SlideShare a Scribd company logo
1 of 16
Download to read offline
Crowd characterization
from computer vision
by Federico
KARAGULIAN
GENERAL NOTES
(Oct. 2023)
Referred to published
paper
https://www.mdpi.com/2413-
8851/7/2/65
Target Square:
Piazza Duca d’Aosta (Milano, Italy)
subway
subway
railway Central Station
subway
camera
(a) (b)
(c)
The YOLO v3 Model
(pre-processing)
64 by (3x3) Conv + ReLU
Input image:
256x256x3 pixel
32 by (1x1) Conv + ReLU
64 by (3x3) Conv + ReLU
Output: 128x128x3 px
Residual
block
128 by (3x3) Conv + ReLU
64 by (1x1) Conv + ReLU
128 by (3x3) Conv + ReLU
Output: 64x64x3 px
256 by (3x3) Conv + ReLU
32 by (3x3) Conv + ReLU
Down sampling
Down sampling
128 by (1x1) Conv + ReLU
256 by (3x3) Conv + ReLU
Output: 32x32x3 px
512 by (3x3) Conv + ReLU
256 by (1x1) Conv + ReLU
512 by (3x3) Conv + ReLU
Output: 16x16x3 px
1024 by (3x3) Conv + ReLU
512 by (1x1) Conv + ReLU
1024 by (3x3) Conv + ReLU Output: 8x8x3 px
Pre-trained weigths
(COCO dataset)
NN Darknet-53
Residual
block
Down sampling
Residual
block
Residual
block
Residual
block
Down sampling
Down sampling
Figure 2
Up-sampling
Up-sampling
1x
2x
8x
8x
4x
Output: 16x16x3 px
Output: 32x32x3 px
small
medium
large
anchor box &
class assignation
64 by (3x3) Conv + ReLU
Input image:
256x256x3 pixel
32 by (1x1) Conv + identity
64 by (3x3) Conv + identity
Output: 128x128x3 px
Residual
block
128 by (3x3) Conv + ReLU
64 by (1x1) Conv + identity
128 by (3x3) Conv + identity
Output: 64x64x3 px
256 by (3x3) Conv + ReLU
32 by (3x3) Conv + ReLU
Down sampling
Down sampling
128 by (1x1) Conv + identity
256 by (3x3) Conv + identity
Output: 32x32x3 px
512 by (3x3) Conv + ReLU
256 by (1x1) Conv + identity
512 by (3x3) Conv + identity
Output: 16x16x3 px
1024 by (3x3) Conv + ReLU
512 by (1x1) Conv + identity
1024 by (3x3) Conv + identity Output: 8x8x3 px
Pre-trained weigths
(COCO dataset)
YOLOv3 - NN Darknet-53
Residual
block
Down sampling
Residual
block
Residual
block
Residual
block
Down sampling
Down sampling
1x
2x
8x
8x
4x
small
medium
large
class
assignation
Postprocessing from YOLOv3 model results
➢ From pixels to meters (from 3D to 2D view using conversion factors that
considered the view angle of the camera, the viewpoint depth of the image and
top view dimensions of the Piazza.
➢ trajectories estimation by tracking each unique identifier and by construction of
time series of locations each minute
➢ Calculation of mean speed along each trajectory (= distance/trajectory duration)
➢ Calculation of “instantaneous” speed
➢ Filtering speed (> 0.3 & < 2.5 m/s)
➢ Calculation of the direction of the trajectory (in degrees) from ORIGIN --> DESTINATION for each ID
To build heatmaps:
➢ Convert position of each trajectory point into a projected coordinate system in meters
(projection epsg:32632, WGS 84/UTM zone 32N)
➢ Definition of a regular grid of 2x2m square cells
➢ Intersection of trajectory data with the grid
➢ Average of speed and direction data within each grid cell at time intervals of 15 minutes
and during morning/evening hours
➢ Calculation of Voronoi areas for each point (not per trajectory) (for density calculation)
➢ Intersection of density data with the grid
➢ Average of voronoi density within each grid cell at time intervals of 15 minutes
and during morning/evening hours
Post-processing
Identification of single ID
(ID == pedestrian)
Person - 1771
Person - 1771
Person - 1771
Person - 1771
Person - 1771
Person - 1771
Person - 1771
Person - 1771
Person - 1771
Person - 1771
Person - 1771
Person - 1771
Person - 1771
Person - 1771
subway
subway
General considerations about trajectories and speed:
Data cleaning
1) if distance between two consecutive traces >=1m,
2) if the distance with the previous point <=1m,
3) if distance with the two next points <=1m
4) if the timestamp difference (in seconds) between two consecutive traces is < 1 second
Filtering angles with criteria to avoid erroneous directions
5) If absolute angle between two consecutive directions is >= 90°, the trace is ignored
Targeting constant directions
6) Filtering data withing 10-30 seconds time accroding to defined directions
7) group_by directions with the highest number of recurrencies
Considerations
Most of trajectories are from the north to south
Most of pedestrians come from the subway located on the top-right side of the Piazza Duca d’Aosta
METRICS
Accuracy: ratio between the number of the DETECTED
pedestrians and the effectively TRACKED persons in each frame
Confidence: how much we are confident the DETECTED object
is a person (pedestrian) from Computer Vision
IoU: Intersection over Union, allows evaluating how similar a
predicted bounding box is to the ground truth box.
(IoU) is known to be a good metric for measuring overlap between two
bounding boxes or masks.
MOTA: Multiple Object Tracking Accuracy
MOTP: Multiple Object Tracking Precision (must be close to zero as
much as possible)
Clustering directions and Speed (morning and evening)
Speed Heat-maps
Spatial representation of identified pedestrians from CV
a) Three main clusters of pedestrian were found
b) Centroid of the clusters were localized in the proximity
of the subway access points (A) and in the middle of
the square (B) Piazza Duca d’Aosta in front of the
central station.
Mean SPEED heatmaps of pedestrians.
Speeds have been computed for every
trajectory of each pedestrian ID by
considering spatial increment within 1 sec.
Speed values were averaged every 15
minutes.
➢ Speed were filtered for considering a minimum
forward speed of 0.3 [m/s] and a maximum
speed of 2.5 [m/s].
➢ High speed values were observed at the centre
of the square while subway access points
showed homogeneous speeds
Density Heat-maps
(with Voronoi
Assumption)
Mean DENSITY heatmaps of pedestrians.
Density was computed as the ratio between the
number of pedestrian
within 2x2m2 cell and the area of the cell weighted
by the number of timestamps.
STATS
Density Heat-maps
(with Voronoi
Assumption)
for technical details contact:
federico.karagulian@enea.it
or
karafede@hotmail.com

More Related Content

Similar to Computer Vision

Investigation of repeated blasts at Aitik mine using waveform cross correlation
Investigation of repeated blasts at Aitik mine using waveform cross correlationInvestigation of repeated blasts at Aitik mine using waveform cross correlation
Investigation of repeated blasts at Aitik mine using waveform cross correlationIvan Kitov
 
Random Chaotic Number Generation based Clustered Image Encryption
Random Chaotic Number Generation based Clustered Image EncryptionRandom Chaotic Number Generation based Clustered Image Encryption
Random Chaotic Number Generation based Clustered Image EncryptionAM Publications
 
"What is Neuromorphic Event-based Computer Vision? Sensors, Theory and Applic...
"What is Neuromorphic Event-based Computer Vision? Sensors, Theory and Applic..."What is Neuromorphic Event-based Computer Vision? Sensors, Theory and Applic...
"What is Neuromorphic Event-based Computer Vision? Sensors, Theory and Applic...Edge AI and Vision Alliance
 
SSII2018企画: センシングデバイスの多様化と空間モデリングの未来
SSII2018企画: センシングデバイスの多様化と空間モデリングの未来SSII2018企画: センシングデバイスの多様化と空間モデリングの未来
SSII2018企画: センシングデバイスの多様化と空間モデリングの未来SSII
 
Model-counting Approaches For Nonlinear Numerical Constraints
Model-counting Approaches For Nonlinear Numerical ConstraintsModel-counting Approaches For Nonlinear Numerical Constraints
Model-counting Approaches For Nonlinear Numerical ConstraintsQuoc-Sang Phan
 
System Monitoring
System MonitoringSystem Monitoring
System Monitoringbutest
 
CVS vs. t2 -x 2 velocity analysis
CVS vs. t2 -x 2 velocity analysisCVS vs. t2 -x 2 velocity analysis
CVS vs. t2 -x 2 velocity analysisiosrjce
 
Project session part_I
Project  session part_IProject  session part_I
Project session part_IMina Yonan
 
Multi-slot Coded ALOHA with Irregular Degree.pdf
Multi-slot Coded ALOHA with Irregular Degree.pdfMulti-slot Coded ALOHA with Irregular Degree.pdf
Multi-slot Coded ALOHA with Irregular Degree.pdfYAAKOVSOLOMON1
 
group-3-a21-traverse-report.pdf
group-3-a21-traverse-report.pdfgroup-3-a21-traverse-report.pdf
group-3-a21-traverse-report.pdfNkosiAnsari
 
IJCER (www.ijceronline.com) International Journal of computational Engineeri...
 IJCER (www.ijceronline.com) International Journal of computational Engineeri... IJCER (www.ijceronline.com) International Journal of computational Engineeri...
IJCER (www.ijceronline.com) International Journal of computational Engineeri...ijceronline
 
A New Key Stream Generator Based on 3D Henon map and 3D Cat map
A New Key Stream Generator Based on 3D Henon map and 3D Cat mapA New Key Stream Generator Based on 3D Henon map and 3D Cat map
A New Key Stream Generator Based on 3D Henon map and 3D Cat maptayseer Karam alshekly
 
IMAGE ENCRYPTION BASED ON DIFFUSION AND MULTIPLE CHAOTIC MAPS
IMAGE ENCRYPTION BASED ON DIFFUSION AND MULTIPLE CHAOTIC MAPSIMAGE ENCRYPTION BASED ON DIFFUSION AND MULTIPLE CHAOTIC MAPS
IMAGE ENCRYPTION BASED ON DIFFUSION AND MULTIPLE CHAOTIC MAPSIJNSA Journal
 
The GRASS GIS software (with QGIS) - GIS Seminar
The GRASS GIS software (with QGIS) - GIS SeminarThe GRASS GIS software (with QGIS) - GIS Seminar
The GRASS GIS software (with QGIS) - GIS SeminarMarkus Neteler
 
Udacity-Didi Challenge Finalists
Udacity-Didi Challenge FinalistsUdacity-Didi Challenge Finalists
Udacity-Didi Challenge FinalistsDavid Silver
 

Similar to Computer Vision (20)

Poster
PosterPoster
Poster
 
Investigation of repeated blasts at Aitik mine using waveform cross correlation
Investigation of repeated blasts at Aitik mine using waveform cross correlationInvestigation of repeated blasts at Aitik mine using waveform cross correlation
Investigation of repeated blasts at Aitik mine using waveform cross correlation
 
Random Chaotic Number Generation based Clustered Image Encryption
Random Chaotic Number Generation based Clustered Image EncryptionRandom Chaotic Number Generation based Clustered Image Encryption
Random Chaotic Number Generation based Clustered Image Encryption
 
"What is Neuromorphic Event-based Computer Vision? Sensors, Theory and Applic...
"What is Neuromorphic Event-based Computer Vision? Sensors, Theory and Applic..."What is Neuromorphic Event-based Computer Vision? Sensors, Theory and Applic...
"What is Neuromorphic Event-based Computer Vision? Sensors, Theory and Applic...
 
Sensor Robotics.ppt
Sensor Robotics.pptSensor Robotics.ppt
Sensor Robotics.ppt
 
SSII2018企画: センシングデバイスの多様化と空間モデリングの未来
SSII2018企画: センシングデバイスの多様化と空間モデリングの未来SSII2018企画: センシングデバイスの多様化と空間モデリングの未来
SSII2018企画: センシングデバイスの多様化と空間モデリングの未来
 
Model-counting Approaches For Nonlinear Numerical Constraints
Model-counting Approaches For Nonlinear Numerical ConstraintsModel-counting Approaches For Nonlinear Numerical Constraints
Model-counting Approaches For Nonlinear Numerical Constraints
 
System Monitoring
System MonitoringSystem Monitoring
System Monitoring
 
CVS vs. t2 -x 2 velocity analysis
CVS vs. t2 -x 2 velocity analysisCVS vs. t2 -x 2 velocity analysis
CVS vs. t2 -x 2 velocity analysis
 
Project session part_I
Project  session part_IProject  session part_I
Project session part_I
 
Multi-slot Coded ALOHA with Irregular Degree.pdf
Multi-slot Coded ALOHA with Irregular Degree.pdfMulti-slot Coded ALOHA with Irregular Degree.pdf
Multi-slot Coded ALOHA with Irregular Degree.pdf
 
Tele immersion
Tele immersionTele immersion
Tele immersion
 
group-3-a21-traverse-report.pdf
group-3-a21-traverse-report.pdfgroup-3-a21-traverse-report.pdf
group-3-a21-traverse-report.pdf
 
IJCER (www.ijceronline.com) International Journal of computational Engineeri...
 IJCER (www.ijceronline.com) International Journal of computational Engineeri... IJCER (www.ijceronline.com) International Journal of computational Engineeri...
IJCER (www.ijceronline.com) International Journal of computational Engineeri...
 
A New Key Stream Generator Based on 3D Henon map and 3D Cat map
A New Key Stream Generator Based on 3D Henon map and 3D Cat mapA New Key Stream Generator Based on 3D Henon map and 3D Cat map
A New Key Stream Generator Based on 3D Henon map and 3D Cat map
 
IMAGE ENCRYPTION BASED ON DIFFUSION AND MULTIPLE CHAOTIC MAPS
IMAGE ENCRYPTION BASED ON DIFFUSION AND MULTIPLE CHAOTIC MAPSIMAGE ENCRYPTION BASED ON DIFFUSION AND MULTIPLE CHAOTIC MAPS
IMAGE ENCRYPTION BASED ON DIFFUSION AND MULTIPLE CHAOTIC MAPS
 
The GRASS GIS software (with QGIS) - GIS Seminar
The GRASS GIS software (with QGIS) - GIS SeminarThe GRASS GIS software (with QGIS) - GIS Seminar
The GRASS GIS software (with QGIS) - GIS Seminar
 
H44093641
H44093641H44093641
H44093641
 
Bf36342346
Bf36342346Bf36342346
Bf36342346
 
Udacity-Didi Challenge Finalists
Udacity-Didi Challenge FinalistsUdacity-Didi Challenge Finalists
Udacity-Didi Challenge Finalists
 

More from Federico Karagulian

SENTINEL- Sistema di Pesatura Dinamico per la gestione del traffico pesante
SENTINEL- Sistema di Pesatura Dinamico per la gestione del traffico pesanteSENTINEL- Sistema di Pesatura Dinamico per la gestione del traffico pesante
SENTINEL- Sistema di Pesatura Dinamico per la gestione del traffico pesanteFederico Karagulian
 
Review on Low Cost Air Quality Sensors
Review on Low Cost Air Quality SensorsReview on Low Cost Air Quality Sensors
Review on Low Cost Air Quality SensorsFederico Karagulian
 
Satellite Remote Sensing (Kasatochi eruption)
Satellite Remote Sensing (Kasatochi eruption)Satellite Remote Sensing (Kasatochi eruption)
Satellite Remote Sensing (Kasatochi eruption)Federico Karagulian
 
Satellite Remote Sensing (Formic Acid)
Satellite Remote Sensing (Formic Acid)Satellite Remote Sensing (Formic Acid)
Satellite Remote Sensing (Formic Acid)Federico Karagulian
 
Particle Matter in Po Valley (Source Apportionment)
Particle Matter in Po Valley (Source Apportionment)Particle Matter in Po Valley (Source Apportionment)
Particle Matter in Po Valley (Source Apportionment)Federico Karagulian
 
Pharmaceuticals: Bioequivalence & Clinical trials
Pharmaceuticals: Bioequivalence & Clinical trialsPharmaceuticals: Bioequivalence & Clinical trials
Pharmaceuticals: Bioequivalence & Clinical trialsFederico Karagulian
 
Mineral Dust and Soot: Atmospheric Chemistry
Mineral Dust and Soot: Atmospheric ChemistryMineral Dust and Soot: Atmospheric Chemistry
Mineral Dust and Soot: Atmospheric ChemistryFederico Karagulian
 
Organics and Sea Salts (Human Health)
Organics and Sea Salts (Human Health)Organics and Sea Salts (Human Health)
Organics and Sea Salts (Human Health)Federico Karagulian
 

More from Federico Karagulian (20)

HEV-TCP ExCo57
HEV-TCP ExCo57HEV-TCP ExCo57
HEV-TCP ExCo57
 
SENTINEL- Sistema di Pesatura Dinamico per la gestione del traffico pesante
SENTINEL- Sistema di Pesatura Dinamico per la gestione del traffico pesanteSENTINEL- Sistema di Pesatura Dinamico per la gestione del traffico pesante
SENTINEL- Sistema di Pesatura Dinamico per la gestione del traffico pesante
 
Vulnerability of road networks
Vulnerability of road networksVulnerability of road networks
Vulnerability of road networks
 
RAFAEL project
RAFAEL projectRAFAEL project
RAFAEL project
 
MOSORE_BRESCIA
MOSORE_BRESCIAMOSORE_BRESCIA
MOSORE_BRESCIA
 
FCD mobile app
FCD mobile appFCD mobile app
FCD mobile app
 
Review on Low Cost Air Quality Sensors
Review on Low Cost Air Quality SensorsReview on Low Cost Air Quality Sensors
Review on Low Cost Air Quality Sensors
 
Dust Detection in the UAE
Dust Detection in the UAEDust Detection in the UAE
Dust Detection in the UAE
 
Task Data Scientist
Task Data ScientistTask Data Scientist
Task Data Scientist
 
Patent_(FK)_EP 2 857 627 A1
Patent_(FK)_EP 2 857 627 A1Patent_(FK)_EP 2 857 627 A1
Patent_(FK)_EP 2 857 627 A1
 
Patent_(FK)_EP 2 843 177 B1
Patent_(FK)_EP 2 843 177 B1Patent_(FK)_EP 2 843 177 B1
Patent_(FK)_EP 2 843 177 B1
 
Sviluppo Sostenibile
Sviluppo SostenibileSviluppo Sostenibile
Sviluppo Sostenibile
 
Satellite Remote Sensing (Kasatochi eruption)
Satellite Remote Sensing (Kasatochi eruption)Satellite Remote Sensing (Kasatochi eruption)
Satellite Remote Sensing (Kasatochi eruption)
 
Satellite Remote Sensing (Formic Acid)
Satellite Remote Sensing (Formic Acid)Satellite Remote Sensing (Formic Acid)
Satellite Remote Sensing (Formic Acid)
 
Aerosols and Nephelometers
Aerosols and NephelometersAerosols and Nephelometers
Aerosols and Nephelometers
 
Particle Matter in Po Valley (Source Apportionment)
Particle Matter in Po Valley (Source Apportionment)Particle Matter in Po Valley (Source Apportionment)
Particle Matter in Po Valley (Source Apportionment)
 
Pharmaceuticals: Bioequivalence & Clinical trials
Pharmaceuticals: Bioequivalence & Clinical trialsPharmaceuticals: Bioequivalence & Clinical trials
Pharmaceuticals: Bioequivalence & Clinical trials
 
Mineral Dust and Soot: Atmospheric Chemistry
Mineral Dust and Soot: Atmospheric ChemistryMineral Dust and Soot: Atmospheric Chemistry
Mineral Dust and Soot: Atmospheric Chemistry
 
Organics and Sea Salts (Human Health)
Organics and Sea Salts (Human Health)Organics and Sea Salts (Human Health)
Organics and Sea Salts (Human Health)
 
Equivalence Cigarette
Equivalence CigaretteEquivalence Cigarette
Equivalence Cigarette
 

Recently uploaded

CALL ON ➥8923113531 🔝Call Girls Chinhat Lucknow best sexual service Online
CALL ON ➥8923113531 🔝Call Girls Chinhat Lucknow best sexual service OnlineCALL ON ➥8923113531 🔝Call Girls Chinhat Lucknow best sexual service Online
CALL ON ➥8923113531 🔝Call Girls Chinhat Lucknow best sexual service Onlineanilsa9823
 
Carero dropshipping via API with DroFx.pptx
Carero dropshipping via API with DroFx.pptxCarero dropshipping via API with DroFx.pptx
Carero dropshipping via API with DroFx.pptxolyaivanovalion
 
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...Pooja Nehwal
 
Ravak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxRavak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxolyaivanovalion
 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxolyaivanovalion
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptxAnupama Kate
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz1
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Delhi Call girls
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysismanisha194592
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxJohnnyPlasten
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Callshivangimorya083
 
CebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptxCebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptxolyaivanovalion
 
ALSO dropshipping via API with DroFx.pptx
ALSO dropshipping via API with DroFx.pptxALSO dropshipping via API with DroFx.pptx
ALSO dropshipping via API with DroFx.pptxolyaivanovalion
 
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Delhi Call girls
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFxolyaivanovalion
 
Zuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptxZuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptxolyaivanovalion
 
BabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxBabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxolyaivanovalion
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusTimothy Spann
 

Recently uploaded (20)

CALL ON ➥8923113531 🔝Call Girls Chinhat Lucknow best sexual service Online
CALL ON ➥8923113531 🔝Call Girls Chinhat Lucknow best sexual service OnlineCALL ON ➥8923113531 🔝Call Girls Chinhat Lucknow best sexual service Online
CALL ON ➥8923113531 🔝Call Girls Chinhat Lucknow best sexual service Online
 
Carero dropshipping via API with DroFx.pptx
Carero dropshipping via API with DroFx.pptxCarero dropshipping via API with DroFx.pptx
Carero dropshipping via API with DroFx.pptx
 
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
 
Ravak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxRavak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptx
 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptx
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signals
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysis
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptx
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
 
CebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptxCebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptx
 
ALSO dropshipping via API with DroFx.pptx
ALSO dropshipping via API with DroFx.pptxALSO dropshipping via API with DroFx.pptx
ALSO dropshipping via API with DroFx.pptx
 
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFx
 
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
 
Zuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptxZuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptx
 
BabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxBabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptx
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and Milvus
 

Computer Vision

  • 1. Crowd characterization from computer vision by Federico KARAGULIAN GENERAL NOTES (Oct. 2023) Referred to published paper https://www.mdpi.com/2413- 8851/7/2/65 Target Square: Piazza Duca d’Aosta (Milano, Italy) subway subway railway Central Station subway camera (a) (b) (c)
  • 2. The YOLO v3 Model (pre-processing)
  • 3. 64 by (3x3) Conv + ReLU Input image: 256x256x3 pixel 32 by (1x1) Conv + ReLU 64 by (3x3) Conv + ReLU Output: 128x128x3 px Residual block 128 by (3x3) Conv + ReLU 64 by (1x1) Conv + ReLU 128 by (3x3) Conv + ReLU Output: 64x64x3 px 256 by (3x3) Conv + ReLU 32 by (3x3) Conv + ReLU Down sampling Down sampling 128 by (1x1) Conv + ReLU 256 by (3x3) Conv + ReLU Output: 32x32x3 px 512 by (3x3) Conv + ReLU 256 by (1x1) Conv + ReLU 512 by (3x3) Conv + ReLU Output: 16x16x3 px 1024 by (3x3) Conv + ReLU 512 by (1x1) Conv + ReLU 1024 by (3x3) Conv + ReLU Output: 8x8x3 px Pre-trained weigths (COCO dataset) NN Darknet-53 Residual block Down sampling Residual block Residual block Residual block Down sampling Down sampling Figure 2 Up-sampling Up-sampling 1x 2x 8x 8x 4x Output: 16x16x3 px Output: 32x32x3 px small medium large anchor box & class assignation
  • 4. 64 by (3x3) Conv + ReLU Input image: 256x256x3 pixel 32 by (1x1) Conv + identity 64 by (3x3) Conv + identity Output: 128x128x3 px Residual block 128 by (3x3) Conv + ReLU 64 by (1x1) Conv + identity 128 by (3x3) Conv + identity Output: 64x64x3 px 256 by (3x3) Conv + ReLU 32 by (3x3) Conv + ReLU Down sampling Down sampling 128 by (1x1) Conv + identity 256 by (3x3) Conv + identity Output: 32x32x3 px 512 by (3x3) Conv + ReLU 256 by (1x1) Conv + identity 512 by (3x3) Conv + identity Output: 16x16x3 px 1024 by (3x3) Conv + ReLU 512 by (1x1) Conv + identity 1024 by (3x3) Conv + identity Output: 8x8x3 px Pre-trained weigths (COCO dataset) YOLOv3 - NN Darknet-53 Residual block Down sampling Residual block Residual block Residual block Down sampling Down sampling 1x 2x 8x 8x 4x small medium large class assignation
  • 5. Postprocessing from YOLOv3 model results ➢ From pixels to meters (from 3D to 2D view using conversion factors that considered the view angle of the camera, the viewpoint depth of the image and top view dimensions of the Piazza. ➢ trajectories estimation by tracking each unique identifier and by construction of time series of locations each minute ➢ Calculation of mean speed along each trajectory (= distance/trajectory duration) ➢ Calculation of “instantaneous” speed ➢ Filtering speed (> 0.3 & < 2.5 m/s) ➢ Calculation of the direction of the trajectory (in degrees) from ORIGIN --> DESTINATION for each ID To build heatmaps: ➢ Convert position of each trajectory point into a projected coordinate system in meters (projection epsg:32632, WGS 84/UTM zone 32N) ➢ Definition of a regular grid of 2x2m square cells ➢ Intersection of trajectory data with the grid ➢ Average of speed and direction data within each grid cell at time intervals of 15 minutes and during morning/evening hours ➢ Calculation of Voronoi areas for each point (not per trajectory) (for density calculation) ➢ Intersection of density data with the grid ➢ Average of voronoi density within each grid cell at time intervals of 15 minutes and during morning/evening hours
  • 7. Identification of single ID (ID == pedestrian)
  • 8. Person - 1771 Person - 1771 Person - 1771 Person - 1771 Person - 1771 Person - 1771 Person - 1771 Person - 1771 Person - 1771 Person - 1771 Person - 1771 Person - 1771 Person - 1771 Person - 1771 subway subway
  • 9.
  • 10. General considerations about trajectories and speed: Data cleaning 1) if distance between two consecutive traces >=1m, 2) if the distance with the previous point <=1m, 3) if distance with the two next points <=1m 4) if the timestamp difference (in seconds) between two consecutive traces is < 1 second Filtering angles with criteria to avoid erroneous directions 5) If absolute angle between two consecutive directions is >= 90°, the trace is ignored Targeting constant directions 6) Filtering data withing 10-30 seconds time accroding to defined directions 7) group_by directions with the highest number of recurrencies Considerations Most of trajectories are from the north to south Most of pedestrians come from the subway located on the top-right side of the Piazza Duca d’Aosta
  • 11. METRICS Accuracy: ratio between the number of the DETECTED pedestrians and the effectively TRACKED persons in each frame Confidence: how much we are confident the DETECTED object is a person (pedestrian) from Computer Vision IoU: Intersection over Union, allows evaluating how similar a predicted bounding box is to the ground truth box. (IoU) is known to be a good metric for measuring overlap between two bounding boxes or masks. MOTA: Multiple Object Tracking Accuracy MOTP: Multiple Object Tracking Precision (must be close to zero as much as possible)
  • 12. Clustering directions and Speed (morning and evening)
  • 13. Speed Heat-maps Spatial representation of identified pedestrians from CV a) Three main clusters of pedestrian were found b) Centroid of the clusters were localized in the proximity of the subway access points (A) and in the middle of the square (B) Piazza Duca d’Aosta in front of the central station. Mean SPEED heatmaps of pedestrians. Speeds have been computed for every trajectory of each pedestrian ID by considering spatial increment within 1 sec. Speed values were averaged every 15 minutes. ➢ Speed were filtered for considering a minimum forward speed of 0.3 [m/s] and a maximum speed of 2.5 [m/s]. ➢ High speed values were observed at the centre of the square while subway access points showed homogeneous speeds
  • 14. Density Heat-maps (with Voronoi Assumption) Mean DENSITY heatmaps of pedestrians. Density was computed as the ratio between the number of pedestrian within 2x2m2 cell and the area of the cell weighted by the number of timestamps.
  • 16. for technical details contact: federico.karagulian@enea.it or karafede@hotmail.com