ABSTRACT
We present a novel application for searching for vehicles in surveillance videos based on semantic attributes. At the interface, the user specifies a set of vehicle characteristics (such as color, direction of travel, speed, length, height, etc.) and the system automatically retrieves video events that match the provided description. A key differentiating aspect of our system is the ability to handle challenging urban conditions such as high volumes of activity and environmental factors. This is achieved through a novel multi-view vehicle detection approach which relies on what we call motionlet classifiers, i.e. classifiers that are learned with vehicle samples clustered in the motion configuration space. We employ massively parallel feature selection to learn compact and accurate motionlet detectors. Moreover, in order to deal with different vehicle types (buses, trucks, SUVs, cars), we learn the motionlet detectors in a shape-free appearance space, where all training samples are resized to the same aspect ratio, and then during test time the aspect ratio of the sliding window is changed to allow the detection of different vehicle types. Once a vehicle is detected and tracked over the video, fine-grained attributes are extracted and ingested into a database to allow future search queries such as "Show me all blue trucks larger than 7ft length traveling at high speed northbound last Saturday, from 2pm to 5pm".
- C. Anagnostopoulos, I. Anagnostopoulos, I. Psoroulas, V. Loumos, and E. Kayafas. License plate recognition from still images and video sequences: A survey. IEEE Transactions on Int. Transp. Systems, 9(3), 2008. Google ScholarDigital Library
- L. Bourdev and J. Malik. Poselets: Body part detectors trained using 3D human pose annotations. In ICCV, 2009.Google ScholarCross Ref
- T. Cootes, G. Edwards, and C. Taylor. Active appearance models. IEEE Transactions on PAMI, 23(6), 2001. Google ScholarDigital Library
- N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In CVPR, 2005: Google ScholarDigital Library
- A. Farhadi, I. Endres, D. Hoiem, and D. Forsyth. Describing objects by their attributes. In CVPR, 2009.Google ScholarCross Ref
- P. Felzenszwalb and R. G. andD. McAllester. Cascade object detection with deformable part models. In CVPR, 2010.Google ScholarCross Ref
- R. Feris, J. Petterson, B. Siddiquie, L. Brown, and S. Pankanti. Large-scale vehicle detection in challenging urban surveillance environments. In WACV, 2011. Google ScholarDigital Library
- A. Hampapur, L. Brown, R. S. Feris, A. Senior, C. Shu, Y. Tian, Y. Zhai, and M. Lu. Searching surveillance video. In AVSS, 2007. Google ScholarDigital Library
- N. Kumar, A. C. Berg, P. N. Belhumeur, and S. K. Nayar. Attribute and simile classifiers for face verification. In ICCV, 2009.Google ScholarCross Ref
- C. H. Lampert, H. Nickisch, and S. Harmeling. Learning to detect unseen object classes by between-class attribute transfer. In CVPR, 2009.Google ScholarCross Ref
- R. Lienhart, L. Liang, and A. Kuranov. A detector tree of boosted classifiers for real-time object detection and tracking. In ICME, 2003. Google ScholarDigital Library
- X. Ma, W. Eric, and L. Grimson. Edge-based rich representation for vehicle classification. In ICCV, 2005. Google ScholarDigital Library
- S. Merler, B. Caprile, and C. Furlanello. Parallelizing AdaBoost by weights dynamics. Computational Statistics & Data Analysis, 51(5):2487--2498, 2007. Google ScholarDigital Library
- P. Perez, M. Gangnet, and A. Blake. Poisson image editing. In SIGGRAPH, 2003. Google ScholarDigital Library
- J. Prokaj and G. Medioni. 3D model based vehicle recognition. In WACV, 2009.Google Scholar
- O. Russakovsky and L. Fei-Fei. Attribute learning in large-scale datasets. In ECCV 2010 Workshop on Parts and Attributes, 2010. Google ScholarDigital Library
- C. Stauffer and W. Grimson. Adaptive background mixture models for real-time tracking. In CVPR, 1998.Google Scholar
- Y. Tian, M. Lu, and A. Hampapur. Robust and efficient foreground analysis for real-time video surveillance. In CVPR, 2005. Google ScholarDigital Library
- D.-C. Tseng and C.-H. Chang. Color segmentation using ucs perceptual attributes. In Proc. Natl. Sci. Council: Part A, volume 18, pages 305--314, 1994.Google Scholar
- D. A. Vaquero, R. S. Feris, D. Tran, L. Brown, and A. Hampapur. Attribute-based people search in surveillance environments. In WACV, 2009.Google ScholarCross Ref
- P. Viola and M. Jones. Robust Real-time Object Detection. In International Journal of Computer Vision, 2001. Google ScholarDigital Library
- B. Wu and R. Nevatia. Cluster boosted tree classifier for multi-view, multi-pose object detection. In ICCV, 2007.Google ScholarCross Ref
Index Terms
- Attribute-based vehicle search in crowded surveillance videos
Recommendations
Real-time multi-vehicle detection and sub-feature based tracking for traffic surveillance systems
CAR'10: Proceedings of the 2nd international Asia conference on Informatics in control, automation and robotics - Volume 2As traffic surveillance technologies continue to grow worldwide, vehicle detection, counting and tracking are becoming increasing important. This paper proposes a real-time multi-vehicle detection and tracking approach. Lane marker detection is carried ...
Real-time vision-based multiple vehicle detection and tracking for nighttime traffic surveillance
SMC'09: Proceedings of the 2009 IEEE international conference on Systems, Man and CyberneticsThis study presents an effective system for detecting and tracking moving vehicles in nighttime traffic scene for traffic surveillance. The proposed method identifies vehicles based on detecting and locating vehicle headlights and taillights by using ...
Training method for vehicle detection
ICCIP '16: Proceedings of the 2nd International Conference on Communication and Information ProcessingRecently, vehicle detection methods have been popularly used in the field of intelligent vehicles. The performance and processing time of vehicle detection is very important because it is associated with the life of a driver. However, all vehicle ...
Comments