CSTalks-Sensor-Rich Mobile Video Indexing and Search-17Aug
1. GeoVid
Geo-referenced Video
Management
Roger Zimmermann, Seon Ho Kim, Sakire Arslan Ay,
Beomjoo Seo, Jia Hao, Guanfeng Wang, Ma He,
Shunkai Fang, Lingyan Zhang, Zhijie Shen
National University University of
of Singapore Southern California
http://geovid.org
9/24/2011 1
2. Outline
I. Introduction & Motivation
II. Scene Modeling & Acquisition
III. Query Processing & Vector Model
IV. Result Presentation
V. Power Management
VI. Synthetic Video Meta-Data Generation
VII.Textual Annotation
2
VIII.Conclusions
9/24/2011 2
3. Outline
I. Introduction & Motivation
II. Scene Modeling & Acquisition
III. Query Processing & Vector Model
IV. Result Presentation
V. Power Management
VI. Synthetic Video Meta-Data Generation
VII.Textual Annotation
3
VIII.Conclusions
9/24/2011 3
4. Motivation (1)
• Trends
– User-generated video content is growing rapidly.
– Mobile devices make it easy to capture video.
• Challenge
– Video is still difficult to manage and search.
• Content-based Image Processing
– It is very desirable to extract
high-level semantic concepts from
images and video
– However, this is tremendously
challenging
9/24/2011 4
5. Motivation (2)
• User-Tagging
– Laborious and often ambiguous or subjective
• Complementary Technique
– Automatically add additional sensor information to the
video during its collection
→ Sensor-rich video
(we also call it geo-referenced video)
– Ex.: location and direction
information can now be collected
through a number of sensors
(e.g., GPS, compass, accelerometer).
9/24/2011 5
6. Motivation (3)
• Recent progress in sensors and integration
Traditionally: Network
Sensors interface
+ + +
Now: Video capturing
Various sensors
WiFi
Handheld mobility
9/24/2011 6
7. Challenges (1)
• Capacity constraint of the battery
• Wireless bandwidth bottleneck
• Searchability of videos
Open-domain video content is very
difficult to be efficiently and accurately
searched
7
9/24/2011 7
8. Challenges (2)
• Video and sensor information storage and indexing
• Result ranking
• Result presentation
8
9/24/2011 8
9. Sensor-Rich Video
• Characteristics:
– Concurrently collect sensor generated geospatial (and
other) contextual data
– Automatic: no user-interaction required
(real-time tagging)
– Data is objective
(however, it may be noisy and/or inaccurate)
→ Generate a time-series of meta-data tags.
• Meta-data can be efficiently searched and processed
and may allow us to deduce certain properties about
the video content.
9/24/2011 9
10. Overview of Approach
1. Viewable scene modeling
2. Video and meta-data acquisition
3. Indexing, querying, and presentation of results
1) 2) 3)
d
9/24/2011 10
11. Outline
I. Introduction & Motivation
II. Scene Modeling & Acquisition
III. Query Processing & Vector Model
IV. Result Presentation
V. Power Management
VI. Synthetic Video Meta-Data Generation
VII.Textual Annotation
11
VIII.Conclusions
9/24/2011 11
12. Viewable Scene Modeling (1)
• More accurately describe the video stream through a camera
field-of-view
• Data collection using sensors
– Camera location from GPS, camera direction from digital
compass, viewing angle from camera parameters
• Details can be found in *ACM MM’08+, *ACM MM’09+
9/24/2011 13
14. Modeling Parameters (DB)
Attributes Explanation
filename Uploaded video file name
<Plat,Plng> <Latitude, longitude> coordinate for camera location
(read from GPS)
altitude The altitude of view point (read from GPS)
alpha Camera heading relative with the ground (read from
compass)
R Viewable distance
theta Angular extent for camera field-of view
tilt Camera pitch relative with the ground (read from
compass)
roll Camera roll relative with the ground (read from compass)
ltime Local time for the FOV
timecode
9/24/201115
9/24/2011 Timecode for the FOV in video (extracted from video) 15
15. Viewable Scene Modeling (3)
• Sensor values are sampled at different intervals
– GPS: 1 per second
– Compass: 40 per second
– Video frames: 30 per second
• Each frame is associated with the temporarily closest
sensor values.
• Interpolation can be used.
• Optimization is implemented for GPS: position is only
measured if movement is more than 10 m.
9/24/2011 16
16. v0.1 Acquisition Prototype
Capture software for
◦ HD video, GPS data
stream, & compass
data stream
GPS
Compass
9/24/2011 17
19. Mobile App Implementation
Data format that stores sensor
data: JSON (JavaScript Object
Video Stream Recorder
Notation)
Location Receiver
Orientation Receiver
Data Storage and
Synchronization Control
Data Uploader
Battery Status Monitor
20
9/24/2011 20
20. Smartphone Acquisition (2)
• Android App
– http://geovid.org/Android/index.html
Available for
download
• iPhone App
– http://geovid.org/iphone/index.html
Will be submitted
to the App Store
9/24/2011 21
21. Outline
I. Introduction & Motivation
II. Scene Modeling & Acquisition
III. Query Processing & Vector Model
IV. Result Presentation
V. Power Management
VI. Synthetic Video Meta-Data Generation
VII.Textual Annotation
22
VIII.Conclusions
9/24/2011 22
22. Spatio-Temporal Search
<-117.010,
46.725>
<-117.013,
46.725>
<-117.013,
Search for the 46.728>
videos of <-117.010,
46.728>
“Kibbie Dome”
<-117.010,
46.725>
<-117.013,
46.725>
<-117.013,
Search for 46.728>
videos that <-117.010,
46.728>
capture the given .
9/24/2011 . 23
trajectory .
23. Query Execution
x time t • Moving cameras:
1
Find relevant
Camera
location x video segments,
but omit irrelevant
x segments
x
Object X
x
x x x x
time t2
9/24/2011 25
25. Querying GeoRef Videos
• Run spatio-temporal range queries
• Extract videos that capture an area of interest:
overlapping region
9/24/2011 27
26. Approach – Search (1)
• FOV model converts the
video search problem
into spatial object
selection problem
• Search only the All objects (n1)
overlapping FOVs (not
Test on simple approximations (n1 objects)
the entire clip) Filter
Step
• Two step approach,
positives (n2) negatives
filter and refinement, is
common in spatial DBs
Test on exact geometry (n2 objects)
• Note that refinement Refinement
step can be very time Step true positives (n3) false positives
consuming in videos
9/24/2011 28
27. Approach – Search (2)
Filter step using MBR
Minimum bounding rectangle
17%
17%
Refinement stepdirectionoverlap
Filter step no checks info!
MBR has checks overlap
FOV Between FOV and query point
between MBR and query point.
Using MBR, meta-data cannot be fully utilized in filter step.
9/24/2011 29
28. Vector Model
Filter step using vector
px
y
V -Vx +Vx
Vy py
Space transformation
p
Vx
x
FOV as vector V -Vy +Vy
Camera location and direction can be used in filter step!
Potential to be more accurate in filtering.
9/24/2011 30
29. Query Processing – Point Query
• Point query
– “For a given query point q qx,qy in 2D geo-space, find all
video frames that overlap with q.”
• Only vectors inside the triangle shaped area in both px-Vx and
py-Vy spaces will remain after the filter step.
query point
2D geo-space px-Vx py-Vy
9/24/2011 The maximum magnitude of any vector is limited to M 31
30. QP – Point Query with r
• Point query with bounded distance r
– “For a given query point q qx,qy in 2D geo-space, find all
video frames that overlap with q, and that were taken
within distance r.”
2D geo-space px-Vx py-Vy
9/24/2011 32
31. QP – Directional Point Query
• Directional Point Query
– “For a given query point q qx,qy in 2D geo-space, find all
video frames taken with the camera pointing in the
Northwest direction and overlapping with q.”
2D geo-space px-Vx py-Vy
9/24/2011 33
32. Vector Model – Implementation
• So far, we represented FOV as a single vector
• Problem: Single-vector model underestimates the
coverage of the FOV.
2D geo-space px-Vx py-Vy
9/24/2011 34
33. Vector Model – Implementation
• Solution: Introduce an overestimation constant ().
Expand the search space by along the V axis.
2D geo-space px-Vx py-Vy
9/24/2011 35
34. Experimental Results
• Implemented smartphone apps with GPS and digital compass;
software for recording video synchronized with sensor inputs.
• Recorded hundreds of real video clips on the street while driving.
• Stored georeferenced video meta-data in a MySQL database .
• Implemented User Defined Functions for queries using vector
model.
• Constructed map-based user interface on the web.
9/24/2011 36
35. Experimental Results
• Purpose of experiments
– Demonstrate the proof-of-concept, feasibility, and
applicability
– No emphasis on performance issues
• Generate random queries and search overlapping video
segments camera position x query point
9/24/2011
Camera positions and query points 37
36. ER – Point Query
• Recall: the number of overlapping FOVs returned by the filter step
the total number of actually overlapping FOVs
• Precision: the number of overlapping FOVs returned in the filter step
the total number of all FOVs returned in the filter step
9/24/2011 38
37. ER – Point Query with Distance r
9/24/2011
“Where is the Pizza Hut?” 39
38. ER – Filtering with Vector Model
• 1,000 random point queries with 10,652 FOVs in the database
• Results from the filter step for the point query with bounded
distance of 50 meters
vector model with different values of overestimation
9/24/2011 constant () 40
39. ER – Directional Point Query
• Results from the filter step for the directional point query
with viewing direction 45o±5o
• MBR has no info about the direction, so it returns all
30,491 FOVs.
• For ≥ 0.3M, the vector model returns 90% less FOVs in
the filter step compared to the MBR.
9/24/2011
(Recall for = 0.3M is 0.948) 41
40. ER – Directional Range Query
• For the directional range query with viewing direction 0 o±5o
Using MBR (no direction) Using Vector (direction: North)
Our search portal - http://geovid.org Skip
9/24/2011 42
41. Outline
I. Introduction & Motivation
II. Scene Modeling & Acquisition
III. Query Processing & Vector Model
IV. Result Presentation
V. Power Management
VI. Synthetic Video Meta-Data Generation
VII.Textual Annotation
43
VIII.Conclusions
9/24/2011 43
42. Query Results: Video Segments
• Example query: Search for the “University of Idaho
Kibbie Dome”.
• The query processed based on the viewable scene
modeling returns more relevant video segments.
9/24/2011 44
44. 2D: Technologies
• LAMP stack (Linux, Apache, MySQL, PHP)
• Google Maps API
• Ajax, XML
• UDF + MySQL
• Flowplayer + Wowza Media Server
9/24/2011 46
45. Results of 2D Presentation
Challenge
• Video is separate from map and requires “mental
orientation” (rotation) that is not intuitive.
Proposed Solution
• Use Google Earth (or other mirror worlds) as a
backdrop to overlay the acquired video clips in the
correct locations and viewing directions.
• Therefore, present the results in 3D.
• Follow the path of the camera trajectory.
9/24/2011 47
48. 3D: Technologies
• LAMP stack (Linux, Apache, MySQL, PHP)
• Google Maps / Google Earth API
• Ajax, XML, KML
• UDF + MySQL
• IFRAME Shim
• HTML5 Video Techniques (Time Seeking)
• 3D Perspective Videos (DrawImage, Canvas)
9/24/2011 50
49. Outline
I. Introduction & Motivation
II. Scene Modeling & Acquisition
III. Query Processing & Vector Model
IV. Result Presentation
V. Power Management
VI. Synthetic Video Meta-Data Generation
VII.Textual Annotation
51
VIII.Conclusions
9/24/2011 51
50. Transmission of
Meta-data and Video
Two simple approaches:
Immediate transmission after capturing through
wireless network
+ Immediate availability of the data
– Consumes lots of energy and bandwidth
Delayed transmission when a faster network is
available
– Sacrifices real
time access
+ Low power consumption
9/24/2011 53
51. Power-Efficient Method
Framework to support an efficient mobile video
capture and transmission.
Observation: not all collected videos have high
priority.
Core idea: separate the small amount of sensor meta-
data from the large video content.
Meta-data is transmitted to a server in real-time.
Video content is searchable by viewable scene
properties established from meta-data attached to each
video.
Video is transmitted in an on-demand manner.
9/24/2011 54
52. System Environment
Sensor Meta-
data Query
Request
Video Request
Message (VRM)
Video Segments
Video Content
Data Acquisition Data Storage and Query
and Indexing Processing
Upload
Key idea: save considerable battery energy by
delaying the costly transmission of the video
segments that have not been requested. 55
9/24/2011 55
53. Linear Regression-based Model
Parameters of the HTC G1 smartphone used in the power model
The overall system power consumption as a function of time t
56
[A. Shye, B. Sholbrock, and G. Memik. Into The Wild: Studying Real User Activity Patterns to Guide Power
Optimization for Mobile Architectures. In Micro, 2009.]
9/24/2011 56
54. Validation of Power Model
Screenshot of the
PowerTutor
Power model vs.
PowerTutor.
[B. Tiwana and L. Zhang. PowerTutor.
http://powertutor.org, 2009.]
9/24/2011 57
55. Simulator Architecture
Modules Immediate OnDemand
14.3km13.6km Network Evaluation Metrics
N AP Topology
w Generator AP Layout
N node Node Energy
ts Consumption
Trajectory Execution
T Generator Trajectory Plan Engine
Power
c Video+FOV Model Query Response
Dc Generator FOV Scene Plan Latency
q
Query Transmitted
Mq
Generator Query List Data
h
60
[Brinkhoff. A framework for generating network-based moving objects. 02]
9/24/2011 60
56. Query Model
Query workload: a list of query rectangles that are mapped to
specific locations
h: generate different distributions of queries
Spatial query distribution with three different clustering
parameter values h
h=0 h=0.5 h=1
9/24/2011 61
57. Performance:
Without Battery Recharging
Closed system where batteries cannot be recharged.
Number of nodes alive. Query response latency.
Node lifetimes and query response latency with
9/24/2011
N = 2,000 nodes. 62
58. Performance:
With Battery Recharging
Mobile node density will eventually reach a dynamic equilibrium.
Energy consumption and access latency with increasing
meta-data upload period.
9/24/2011 63
59. Performance:
With Battery Recharging
Energy consumption and average query response latency with
64
varying number of access points.
9/24/2011 64
60. Performance:
With Battery Recharging
Energy consumption and average Total transmitted data size
query response latency with as a function of query
varying query clustering clustering parameter h.
9/24/2011 parameter h. 65
61. Hybrid Strategy
Overall energy consumption and query response latency when
using a hybrid strategy with both Immediate and OnDemand as
66
a function of the switching threshold (h=0.5).
9/24/2011 66
62. Outline
I. Introduction & Motivation
II. Scene Modeling & Acquisition
III. Query Processing & Vector Model
IV. Result Presentation
V. Power Management
VI. Synthetic Video Meta-Data Generation
VII.Textual Annotation
67
VIII.Conclusions
9/24/2011 67
63. Real-World Video Collection
“Capture the sensor inputs and fuse them with the video streams”
Recorded 134 video clips using the recording prototype system
in Moscow, ID (total 170 mins video).
Videos covered a 6km by 5km region quite uniformly.
Average camera movement speed was 27km/h, and average
camera rotation was around 12 degrees/s.
Collected meta-data included 10,652 FOV scenes in total.
9/24/2011 68
64. Real-World Video Collection
Challenges
The collected real-world video data has not been large
enough to evaluate realistic applications on the large
scale.
Collecting real-world data requires considerable
time and effort.
A complementary solution is to synthetically generate
georeferenced video meta-data.
9/24/2011 69
65. Synthetic Video
Meta-data Generation
Input: Camera Template Specification
Camera movement computation
TIGER/Line
The Brinkhoff Algorithm The GSTD Algorithm
Files
Merge Trajectories
network-based mixed free
movement movement movement
Camera direction computation
Calculate Moving Direction
Adjust Directions on
Randomize Direction Angles
Turns
Output: Georeferenced Video Meta-data
9/24/2011 70
66. Camera Movement
Computation (1)
Network-based Movement
Cameras move on a road-network
Adopted the Brinkhoff algorithm for camera trajectory generation
Introduced stops and acceleration/ deceleration events at some road
crossings and transitions
Camera accelerates with a constant rate(user defines the acceleration rate)
In a deceleration event reduction in
camera speed is simulated based on
the Binomial distribution
B(n, p)
vnext v prev
n
When n=20 and p=0.5 speed is
reduced to half at every time instant
9/24/2011 71
67. Camera Movement
Computation (2)
Free Camera Movement
Cameras move freely.
Improved the GSTD algorithm to generate the camera trajectories with
unconstrained movement:
Added speed control mechanism
Camera movement data is generated in geographic coordinate system
(i.e., as latitude/longitude coordinates)
9/24/2011 72
68. Camera Movement
Compuation (3)
Mixed Camera Movement
Cameras sometimes follow the network and sometimes move randomly on an
unconstraint path.
i. Generate a network based
trajectory (Tinit)
ii. Randomly select n sub-segments
(S1 through Sn) on the trajectory
0|Si| (Tinit/4) and Nrand= (Si) /
|Tinit|)
(user defines Nrand)
i. Replace Si with Trand(i)
ii. Update timestamps
9/24/2011 73
69. Camera Rotation
Compuation (1)
Assigning meaningful camera direction angles is one of the novel
features of the proposed data generator.
Camera direction computation
Calculate Moving Direction
Adjust Directions on
Randomize Direction Angles
Turns
Output: Georeferenced Video Meta-data
Fixed camera: Random rotation camera:
1) Calculate moving direction 1) Calculate moving direction
2) Adjust directions on turns 2) Adjust directions on turns
3) Randomize direction angles
9/24/2011 74
70. Camera Rotation
Computation (2)
Fixed Camera
1) Calculate moving direction 2) Adjust directions on turns
Trajectory Tk
t1
t2
Rotation angle from t1 to t2 is Smooth down the rotation by
larger than max (i.e., distributing the rotation
rotation threshold) amount forwards and
backwards
is the moving direction vector at time t
9/24/2011 75
71. Camera Rotation
Computation (3)
Fixed Camera
Real-world data Synthetic data before Synthetic data after
direction adjustment direction adjustment
Illustration of camera direction adjustment for vehicle cameras
9/24/2011 76 76
72. Camera Rotation
Computation (3)
Randomly Rotating Camera
1) Calculate moving direction
2) Adjust directions on turns
3) Randomize direction angles
Randomly rotate the directions
at each sample point towards left
or right
Rotation amount is inversely
proportional to the current
camera speed level
The rotation amount is
guaranteed to be less than
rotation threshold max
9/24/2011 77
73. Experimental Evaluation (1)
Goal: Evaluate the effectiveness of the synthetic data generation approach
through a high level comparison between the real-world and synthetic data.
Datasets:
Generated two groups of synthetic data:
1. Using vehicle camera template
2. Using passenger camera template
Both synthetic data groups were created based on the road network of
Moscow, ID.
Methodology:
Analyze and compare the movements and rotations of real-world and
synthetic datasets.
Report:
1. The average and maximum values for speed and rotation
2. Frequency distribution of different speed and rotation levels
9/24/2011 78
74. Experimental Evaluation (2)
Comparison of Camera Movement Speed
Maximum speed (km/h) Average speed (km/h) StdDev of speed
Synthetic data with fixed camera 87.91 27.14 12.82
Synthetic data with free camera rotation 87.28 27.32 13.01
Real-world data 0.564 27.03 13.68
Characteristics of the camera speed
Real-world data Synthetic data
Comparison of camera speed distributions for
real-world dataof camera movement speed on map
Illustration and synthetic data with fixed
camera
9/24/2011 79
75. Experimental Evaluation (3)
Comparison of Camera Rotation
Maximum rotation(degrees/s) Average rotation(degrees/s) StdDev of rotation
Synthetic data with fixed camera 32.33 4.64 7.24
Synthetic data with free camera rotation 55.27 12.59 9.35
Real-world data 107.30 11.53 14.02
Characteristics of the camera rotation ( max =60 degrees)
Comparison of camera rotation distributions for Comparison of camera rotation distributions for
real-world data and synthetic data with fixed real-world dataSynthetic data data with random
and synthetic
camera Real-world data
rotation camera
Illustration of camera rotation on map
9/24/2011 80
76. Experimental Evaluation (4)
Performance Issues
The measured data generation times for different types of datasets and
parameter settings
Camera Template Trajectory Rotation Pattern Number of Time to Generate camera Time to Assign Total Time
Pattern Videos trajectory (s) Directions
Vehicle camera Tnetwork Fixed camera 2,980 124 39 163
Passenger camera Tnetwork Random rotation 2,980 115 201 316
Pedestrian camera Tfree Random rotation 2,970 32 263 255
Pedestrian camera Tmixed Random rotation 2,970 271 215 486
The generator can create synthetic datasets in a reasonable amount of time
with off-the-shelf computational resources
9/24/2011 81
77. Summary
Proposed a two step synthetic data generation
1. Computation of the camera movements
2. Computation of the camera movements
Compared the high-level properties of the
synthetically generated data and those of real-
world georeferenced video data.
The synthetic meta-data exhibit equivalent
characteristics to the real data, and hence can be
used in a variety of mobile video management
research.
9/24/2011 82
78. Outline
I. Introduction & Motivation
II. Scene Modeling & Acquisition
III. Query Processing & Vector Model
IV. Result Presentation
V. Power Management
VI. Synthetic Video Meta-Data Generation
VII.Textual Annotation
83
VIII.Conclusions
9/24/2011 83
80. Motivation (2)
• Tech advance in geo-information systems:
– More comprehensive data
– Better usability
– Nicer visualization
9/24/2011 85
81. Motivation (3)
• Tech advance in the manufacturing of smart
phones
– Mobile OS, various sensors, large storage, long
battery life*
• Content-based methods
– Still difficult to bridge the semantic gap
– High computation cost
9/24/2011 86
82. Target (1)
• Bridging the semantic gap: tagging
Marina Bay Sands, Marina Bay,
Singapore, cloudy, etc.
9/24/2011 87
83. Target (2)
• Bridging the semantic gap: tagging
Viewable scene model
Marina Bay Sands, Marina Bay,
Singapore, cloudy, etc.
Geo-information systems
9/24/2011 88
87. Visible Object Computation (3)
• For each FoV, compute the visible objects, and
their visible angle ranges
• Three types of objects:
– Front
– Vertically visible
– Occluded
9/24/2011 92
88. Visible Object Computation (4)
• Horizontally split the FoV into an number
atomic sectors that contains a unique list of
candidate objects
• Vertically check the object visibility
9/24/2011 93
89. Visible Object Computation (4)
• Repeat the process for every FoVs of the video
• Extract textual information
– ID, name, type, coordinates, center, address,
description, websites (external links)
– From OpenStreetMap, GeoDeck
– Able to expanding the sources (e.g., Wikipedia)
9/24/2011 94
90. Tag Ranking & Associating (1)
• The visible objects are not equally relevant to
the video
• More tags are generated with our method
– SG dataset: 60
– USC dataset: 49
9/24/2011 95
91. Tag Ranking & Associating (2)
• 6 basic visual criteria
– Closeness to the FoV center
– Distance to the camera location
– Horizontally visible angle range of the object
– Vertically visible angle range of the object
– Horizontally visible percentage of the object
– Vertically visible percentage of the object
• Additional hints from GIS or external sources
– Special property (e.g., attraction, landmark …)
– Wikipedia entry
9/24/2011 96
92. Tag Ranking & Associating (3)
• Exploiting the temporal existence of the
object
• Associating the tag to a specific segment
9/24/2011 97
93. Evaluation (1)
• Implement prototype
• Collect sample videos
• Compare to YouTube auto-generated tags
• User study
– Familiarity to the place
– Relevance of our tags
– Relevance of YouTube tags
– Preference to our of YouTube tags
– User ranking
9/24/2011 98
96. Outline
I. Introduction & Motivation
II. Scene Modeling & Acquisition
III. Query Processing & Vector Model
IV. Result Presentation
V. Power Management
VI. Synthetic Video Meta-Data Generation
VII.Textual Annotation
101
VIII.Conclusions
9/24/2011 101
97. Conclusions
• Annotation using sensors can provide automatic and
objective meta-data for indexing and searching.
• Georeferenced video search has a great potential,
especially in searching user generated videos.
• Many open questions:
– Standard format of meta-data
– Standard way of embedding meta-data
– Index structures of meta-data for fast searching
– Supporting new query types
– Combining with content based features
– Relevance ranking for result presentation
9/24/2011 102
98. Thank You
Further information at:
http://geovid.org
rogerz@comp.nus.edu.sg
9/24/2011
seonkim@usc.edu 104
99. Relevant Publications (1)
[ACM MM ’08]
Sakire Arslan Ay, Roger Zimmermann, Seon Ho Kim
Viewable Scene Modeling for Geospatial Video Search
ACM Multimedia Conference (ACM MM 2008), Oct. 2008.
[ACM MM ’09]
Sakire Arslan Ay, Lingyan Zhang, Seon Ho Kim, Ma He, Roger Zimmermann
GRVS: A Georeferenced Video Search Engine
ACM Multimedia Conference (ACM MM 2009), Technical Demo, Oct. 2009.
[MMSJ ’10]
Sakire Arslan Ay, Roger Zimmermann, Seon Ho Kim
Relevance Ranking in Georeferenced Video Search
Multimedia Systems Journal, Springer, 2010.
[MMSys ’11]
Seon Ho Kim, Hao Jia, Sakie Arslan Ay, Roger Zimmermann
Energy-Efficient Mobile Video Management using Smartphones
ACM Multimedia Systems Conference (ACM MMSys 2011), Feb. 2011.
9/24/2011 105
100. Relevant Publications (2)
[ACM MM ’11]
Zhijie Shen, Sakire Arslan Ay, Seon Ho Kim, Roger Zimmermann
Automatic Tag Generation and Ranking for Sensor-rich Outdoor Videos
ACM Multimedia Conference (ACM MM 2011), Nov. 2011.
[ACM MM ’11]
Zhijie Shen, Sakire Arslan Ay, Seon Ho Kim
SRV-TAGS: An Automatic TAGging and Search System for Sensor-Rich Outdoor Videos
ACM Multimedia Conference (ACM MM 2011), Technical Demo, Nov. 2011.
[ACM MM ’11]
Hao Jia, Guanfeng Wang, Beomjoo Seo, Roger Zimmermann
Keyframe Presentation for Browsing of User-generated Videos on Map Interface
ACM Multimedia Conference (ACM MM 2011), Short Paper, Nov. 2011.
[ACM MM ’11]
Beomjoo Seo, Jia Hao, Guanfeng Wang
Sensor-rich Video Exploration on a Map Interface
ACM Multimedia Conference (ACM MM 2011), Technical Demo, Nov. 2011.
9/24/2011 106