Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Sparse Mat: A Tale of Devising A Low-Cost Directional System for Pedestrian Counting

334 views

Published on

Pedestrian counting is required in diversified places such as shopping malls, touristic spots, etc., however, a low-cost solution to this problem is yet to be proposed in the literature. Therefore, in this paper, we propose a new solution for pedestrian counting that exploits only a small number of COTS sensors (94% less than that used in the existing Eco-Counter solution). To do so, we propose detail designs and two different algorithms for separately sensing step-down and step-up phenomena that we find while walking. User evaluation of real implementations of both our algorithms confirms an average accuracy of up to 93% through sensing the step-up phenomena.

Published in: Devices & Hardware
  • Hey guys! Who wants to chat with me? More photos with me here 👉 http://www.bit.ly/katekoxx
       Reply 
    Are you sure you want to  Yes  No
    Your message goes here

Sparse Mat: A Tale of Devising A Low-Cost Directional System for Pedestrian Counting

  1. 1. Sparse Mat: A Tale of Devising A Low-Cost Directional System for Pedestrian Counting Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh NSysS 2017 Dhaka, Bangladesh Tarik Reza Toha, Salman Estyak, Taslim Arefin Khan, Tusher Chakraborty, and A. B. M. Alim Al Islam
  2. 2. Outline • Background and motivation • Our proposed system – Design – Implementation – Experimentation • User evaluation • Conclusion and future work 2
  3. 3. Background: Pedestrian Counting 3
  4. 4. Applications of Pedestrian Counting • Strategic business research – Tourist flow estimation • Security and emergency support – Victim count estimation for rescue operations • Optimization tasks – Railway stations, shopping malls, airports, hospitals, etc. 4 Assign staff deployment to demand
  5. 5. Classical Pedestrian Counting Technique 5 • Low human mobility – Using pen and paper, or tally counter • High human mobility – Automated pedestrian counter is required
  6. 6. Existing Automated Counting Techniques 6 Pros:  High accuracy Cons:  High cost  High power Pros:  Low-cost  Low-power  Easy setup process Cons:  Low accuracy Laser scanner counter [Katabira et al., ACRS, 2004] Infrared beam counter [Wienand et al., USPTO, 2001] Cons:  High cost  Complex algorithms  High processing power Pros:  High accuracy Camera-based counter [Agusta et al., ICCEMS, 2014] Existing high-end device based solutions are high-cost and high-power
  7. 7. Existing Mat-Based Counting Technologies 7 Greneker et al., 1996 (2000 sensors/sq. ft.) Kutschera et al., 2011 (90 sensors/sq. ft.) Instant Counting Mat by Milon et al., 2013 (56 sensors/sq. ft.) Existing mat-based solutions demand high densities of expensive sensors
  8. 8. Our Contribution 8 We propose a mat-based pedestrian counting solution comprising low density (~3 sensors/sq. ft.) of low-cost sensors, which exhibits a high accuracy in pedestrian counting Sparse Mat
  9. 9. Underlying Sensing Mechanism 9
  10. 10. Sparse Mat: Operational Block Diagram 10 Block diagram Cross sectional view of sensing module
  11. 11. Snapshot of Sparse Mat 11 Sensing Module Controller Module
  12. 12. Piezoelectric Sensor Responses for Varying Radial Distances 12 Piezoelectric sensor responses under varying points of pressure over the hardboard block Coverage of piezoelectric sensor response Vibration propagation while knocking on a hardboard block, which covered a piezoelectric sensor
  13. 13. Sensing Step-Down Phenomena 13 Sensor placement over mat Sensor placement along with taped foam Hardboard block placement over sensors
  14. 14. Findings from 2×2 Piezo-grid 14 Piezoelectric sensor responses while moving towards from down row to up row over the left sensors Piezoelectric sensor responses while moving towards from up row to down row over the right sensors drdl ul ur drdl ul ur The varying response time can significantly undermine the accuracy of directional pedestrian counting
  15. 15. Resilience to Variation in Response Time: 2×3 Piezo-grid? 15 Sensor placement over mat Sensor placement along with taped foam Hardboard block placement over sensors
  16. 16. Findings from 2×3 Piezo-grid 16 Piezoelectric sensor responses while moving towards from down row to up row Piezoelectric sensor responses while moving towards from up row to down row drdl ul ur dm um drdl ul ur dm um The ending always maintains perfect order even though starting may not!
  17. 17. Sensing Step-up Phenomena 17
  18. 18. Modified Settings in 2×3 Piezo-grid 18 Sensor placement over mat Sensor placement along with taped foam Hardboard block placement over sensors
  19. 19. Enhancing Sensing Accuracy: 3×2 Piezo-grid 19 Sensor placement over mat Sensor placement along with taped foam Hardboard block placement over sensors
  20. 20. User Evaluation of Preliminary Designs Grid Sensing Phenomena Accuracy (%) Causes 2×2 Step-Down < 50 Response time varies significantly from sensor to sensor 2×3 Step-Down 60 Time delay between placing heel and toe is very small 2×3 Step-Up 75 Participants often failed to place their foot step over both hardboard blocks 20
  21. 21. User Evaluation of the Final Design: 3×2 Piezo-grid Sensing Step-Up Age Height (inch) Weight (kg) Shoe length (inch) Total attempts Successful detection Device accuracy (%) 22 66 68 11 18 14 78 22 70 62 11.25 20 20 100 22 73 81 12 10 8 80 23 70 90 11.25 20 20 100 25 68 72 11.25 20 20 100 26 66 55 11 8 7 88 Total 96 89 93 21
  22. 22. Conclusion and Future Work • Existing automated directional pedestrian counters are generally highly expensive • We propose a low-cost and easily-to-deploy automated directional pedestrian counter without compromising accuracy – Uses sparser sensors than any other state-of-the-art technologies  94% sparser than Instant Counting Mat – User evaluation of real implementations confirms an average accuracy of 93% • Future work – Workable for different types of users such as kids – Determine multiple footsteps of a single person – Determine multiple persons traversing in parallel over the sensor mat 22
  23. 23. A Short Demonstration of Sparse Mat 23 • https://youtu.be/C7MB58Xvr_w
  24. 24. Thank you Questions are welcome! Email: tarik.toha@gmail.com 24
  25. 25. Variable Sensor Response Times 25
  26. 26. Towards Sensing Step-up Phenomena (contd.) 26 Flowchart of step-down phenomena sensing algorithm Flowchart of step-up phenomena sensing algorithm

×