Feng Min
ABSTRACT
People counting based on surveillance camera is the basis of the important tasks, such as the analysis of crowd behavior, the optimal allocation of resources and public security. Aiming at the low accuracy of the people counting method based on object detection, a people counting method based on multi-scale region adaptive segmentation and deep neural network is proposed in this paper. The idea originates from the analysis and research of multi-scale objects, and it is found that the detection accuracy will be improved if the multi-scale objects match the size of multi-scale anchors. In this method, K-means is used to cluster the detection results of Faster-RCNN model. Then the image is segmented adaptively according to the clustered results. Finally, Faster-RCNN model is used to detect the segmented images. The experimental results show that the average accuracy of this method is 45.78% on mall dataset, which is higher than Faster-RCNN about 3.59%.
- Subburaman V B, Descamps A, Carincotte C. Counting People in the Crowd Using a Generic Head Detector[C]//2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance. IEEE, 2012.Google Scholar
- Vu T H, Osokin A, Laptev I. Context-aware CNNs for person head detection[J]. 2015.Google ScholarDigital Library
- Zhang Y, Zhou D, Chen S, et al. Single-Image Crowd Counting via Multi-Column Convolutional Neural Network[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2016.Google Scholar
- He K, Zhang X, Ren S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 37(9): 1904--1916.Google ScholarDigital Library
- Uijlings J R R, Van De Sande K E A, Gevers T, et al. Selective search for object recognition[J]. International journal of computer vision, 2013, 104(2): 154--171.Google Scholar
- Zitnick C L, Dollár P. Edge boxes: Locating object proposals from edges[C]//European conference on computer vision. Springer, Cham, 2014: 391--405.Google Scholar
- Lu Y, Javidi T, Lazebnik S. Adaptive object detection using adjacency and zoom prediction[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016: 2351--2359.Google Scholar
- Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779--788.Google Scholar
- Liu W, Anguelov D, Erhan D, et al. Ssd: Single shot multibox detector[C]//European conference on computer vision. Springer, Cham, 2016: 21--37.Google Scholar
- Xia F, Wang P, Chen L C, et al. Zoom better to see clearer: Human and object parsing with hierarchical auto-zoom net[C]//European Conference on Computer Vision. Springer, Cham, 2016: 648--663.Google Scholar
- GUO Wen-sheng, BAO Ling, et al. People counting method based on adaptive overlapping segmentation and deep neural network, v.45(8):236--242.Google Scholar
- Vora, Aditya, Chilaka, Vinay. FCHD: Fast and accurate head detection in crowded scenes[J].Google Scholar
- Ren S, He K, Girshick R, et al. Faster r-cnn: Towards realtime object detection with region proposal networks[C]//Advances in neural information processing systems. 2015: 91--99.Google Scholar
- Girshick R. Fast r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2015: 1440--1448.Google Scholar
- Wagstaff K, Cardie C, Rogers S, et al. Constrained k-means clustering with background knowledge[C]//Icml. 2001, 1: 577--584.Google Scholar
Index Terms
- People Counting Based on Multi-scale Region Adaptive Segmentation and Depth Neural Network
Recommendations
Deep People Counting with Faster R-CNN and Correlation Tracking
ICIMCS'16: Proceedings of the International Conference on Internet Multimedia Computing and ServiceCrowd counting is a key problem for many computer vision tasks while most existing methods try to count people based on regression with hand-crafted features. Recently, the fast development of deep learning has resulted in many promising detectors of ...
Optic Disc and Fovea Detection Using Multi-Stage Region-Based Convolutional Neural Network
ISICDM 2018: Proceedings of the 2nd International Symposium on Image Computing and Digital MedicineDetection of the optic disc (OD) and fovea in retinal images is an important step for automated detection of retinal disease in digital color photographs of the retina. Together with the vasculature, the optic disc and the fovea are the most important ...
A robust multi-scale deep learning approach for unconstrained hand detection aided by skin segmentation
AbstractRobust detection of hands in images at different scales, especially, small-sized hands, has remained a challenge in computer vision. In this work, we design a multi-scale deep learning algorithm to detect hands in unconstrained scenarios as well ...
Comments