Jia Sun
ABSTRACT
Pedestrian detection is a technique that uses computer vision techniques to determine if there are pedestrians in an image or video sequence and introduces precise positioning. In this paper, a pedestrian detection algorithm is designed for depth information images collected by a low-resolution Time-of-Flight (ToF) camera. First, GoDec algorithm is applied to remove noise and extract the foreground. Then Maximally Stable Extremal Regions (MSER) is employed to roughly segment the head region. Due to adhesion between head and shoulder, some shoulder regions may be falsely segmented by MSER. To overcome this problem, an improved water filling algorithm is proposed to get a fine detection result. Two datasets are constructed in an indoor environment to validate the validity of the proposed method. In the situation of crowding and people with diverse postures, the proposed method gets better detection performance compared with existing methods.
- Wu S, Yu S, Chen W. 2012. An attempt to pedestrian detection in depth images. Intelligent Visual Surveillance. IEEE: 97--100.Google Scholar
- Bevilacqua, Alessandro & Di Stefano, Luigi & Azzari, Pietro. 2006. People Tracking Using a Time-of-Flight Depth Sensor. 2006 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS'06), vol. 6. 89. 10.1109/AVSS.2006.92.Google ScholarDigital Library
- Ali I, Dailey MN. 2012. Multiple human tracking in high-density crowds. Image Vis Comput 30(12): 966--977.Google ScholarDigital Library
- X Zhang, J Yan, S Feng, Z Lei and D Yi. 2012. Water Filling: Unsupervised People Counting via Vertical Kinect Sensor. IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance: 215--220.Google ScholarDigital Library
- Harville M, Li D. 2004. Fast, integrated person tracking and activity recognition with plan-view templates from a single stereo camera. IEEE conference on computer vision and pattern recognition, Washington.Google ScholarCross Ref
- R Tanner, M Studer, A Zanoli and A Hartmann. 2008. People Detection and Tracking with TOF Sensor. IEEE Fifth International Conference on Advanced V: 356--361.Google Scholar
- S Ikemura, H Fujiyoshi. 2012. Human Detection by Haar-like Filtering using Depth Information. International Conference on Pattern Recognition: 813--816.Google Scholar
- E Bondi, L Seidenari, AD Bagdanov and AD Bimbo. 2014. Real-time people counting from depth imagery of crowded environments. International Conference on Advanced Video & Signa: 337--342.Google ScholarCross Ref
- SB Gkt, C Tomasi. 2004. 3D Head Tracking Based on Recognition and Interpolation Using a Time-Of-Flight Depth Sensor. IEEE Computer Society Conference on Computer Vision & Pattern Recognition: 211--217.Google Scholar
- M Rauter. 2013. Reliable Human Detection and Tracking in Top-View Depth Images. IEEE Conference on Computer Vision & Pattern Recognition Workshops: 529--534.Google Scholar
- C Stahlschmidt, A Gavriilidis, J Velten and A Kummert. 2014. Applications for a people detection and tracking algorithm using a time-of-flight camera. Multimedia Tools & Applications: 1--18.Google Scholar
- P Vera, S Monjaraz. 2016. Counting pedestrians with a zenithal arrangement of depth cameras. Machine Vision and Applications: 1--17.Google Scholar
- Tianyi Zhou, Dacheng Tao. 2011. GoDec: Randomized Low-rank & Sparse Matrix Decomposition in Noisy Case. International Conference on Machine Learning: 33--40.Google Scholar
- Matas J, Chum O, Urban M and Pajdla T. 2004. Robust wide-baseline stereo from maximally stable extremal regions. Image and Vision Computing 22(10): 761--767.Google ScholarCross Ref
- Foix S, Aleny`a G and Torras C. 2011. Lock-in time-of-flight (ToF) cameras: a survey. IEEE Sensors. 11(9): 1917--1926. doi: 10.1109/JSEN.2010.2101060Google ScholarCross Ref
- Bondi E, Seidenari L and Bagdanov A D. 2014. Real-time people counting from depth imagery of crowded environments. International Conference on Advanced Video & Signal Based Surveillance. IEEE Computer Society.Google Scholar
- Del Pizzo L, Foggia P and Greco A. 2016. Counting people by RGB or depth overhead cameras. Pattern Recognition Letters: S0167865516301179.Google Scholar
Index Terms
- Pedestrian Detection Based on Depth Information
Recommendations
A novel low false alarm rate pedestrian detection framework based on single depth images
Pedestrian detection is an important image understanding problem with many potential applications. There has been little success in creating an algorithm which exhibits a high detection rate while keeping the false alarm in a relatively low rate. This ...
Real-time pedestrian detection via hierarchical convolutional feature
With the development of pedestrian detection technologies, existing methods can not simultaneously satisfy high quality detection and fast calculation for practical applications. Therefore, the goal of our research is to balance of pedestrian detection ...
G2P: a new descriptor for pedestrian detection
AbstractPedestrian detection plays an important role in many applications. Since its birth 13 years ago, Histogram Of Gradient (HOG) descriptor has become a popular descriptor for pedestrian detection. Besides its original instantiation, the HOG also ...
Comments