Deep convolutional framework for abnormal behavior detection in a smart surveillance system
智能监控系统中异常行为检测的深度卷积框架
Engineering Applications of Artificial Intelligence, Volume 67, January 2018, Pages 226-234
Kwang-Eun Ko, Kwee-Bo Sim
Abstract: The ability to instantly detect risky behavior in video surveillance systems is a critical issue in a smart surveillance system. In this paper, a unified framework based on a deep convolutional framework is proposed to detect abnormal human behavior from a standard RGB image. The objective of the unified structure is to improve detection speed while maintaining recognition accuracy. The deep convolutional framework consists of (1) a human subject detection and discrimination module that is proposed to solve the problem of separating object entities, in contrast to previous object detection algorithms, (2) a posture classification module to extract spatial features of abnormal behavior, and (3) an abnormal behavior detection module based on long short-term memory (LSTM). Experiments on a benchmark dataset evaluate the potential of the proposed method in the context of smart surveillance. The results indicate that the proposed method provides satisfactory performance in detecting abnormal behavior in a real-world scenario.
Recognition of pedestrian activity based on dropped-object detection
基于掉落物品检测的行人行为识别
Signal Processing, Volume 144, March 2018, Pages 238-252
Weidong Min, Yu Zhang, Jing Li, Shaoping Xu
Abstract:Aiming at recognizing dropped objects and matching their owners, this paper presents a method for analyzing pedestrian activity based on dropped-object detection in video surveillance. The recognition results may be applied to further analyzing human activity and intentions such as determining whether the dropped-objects are intentional hazardous or unconsciously lost articles according to the appearance of dropped-objects. The method consists of dropped-object detection and recognition. The dropped-object detection algorithm uses foreground detection based on bi-directional background modeling, MeanShift tracking, and pixel-based regional information at the drop-off point. It analyzes the relationship between the dropped objects and pedestrians at the pixel level in complex environments with noises and occlusions. Afterwards, an algorithm based on moment invariant and Principal Component Analysis (PCA) is proposed to further recognize the dropped-objects viewed from different directions and locations from video cameras. In addition, in order to solve the limitation of the centralized video processing model for large-scale video streams in real time, the proposed method is designed and accomplished in a distributed model. The experimental results showed that the proposed method can effectively and efficiently recognize the pedestrian activity through the dropped objects in real-time video data.
Video feature descriptor combining motion and appearance cues with length-invariant characteristics
结合运动与外貌线索以及长度不变特征的视频特征点描述符
Optik - International Journal for Light and Electron Optics, Volume 157, March 2018, Pages 1143-1154
Tian Wang, Meina Qiao, Yang Chen, Jie Chen, Hichem Snoussi
Abstract:Feature descriptor is one of the important subjects in video analysis problem. In this paper, we propose one video feature descriptor combining motion and appearance cues. The length-invariant characteristics of this proposed feature descriptor are clarified. Further, this feature descriptor is adopted to represent the video sequence for abnormal event detection problem, which is one challenging research field in the video surveillance. We proposed one abnormal event detection algorithm which consists of the feature descriptor and the nonlinear one-class classification method. Experiments on the benchmark dataset and comparisons with the state-of-the-art methods validate the advantages of our proposed feature descriptor.
Depth-based Human Activity Recognition: a comparative perspective study on feature extraction
基于深度的人类行为识别：特征提取比较研究
Future Computing and Informatics Journal, In press, accepted manuscript, Available online 21 December 2017
Heba Hamdy Ali, Hossam M. Moftah, Aliaa A.A. Youssif
Abstract:Depth Maps-based Human Activity Recognition is the process of categorizing depth sequences with a particular activity. In this problem, some applications represent robust solutions in domains such as surveillance system, computer vision applications, and video retrieval systems. The task is challenging due to variations inside one class and distinguishes between activities of various classes and video recording settings. In this study, we introduce a detailed study of current advances in the depth maps-based image representations and feature extraction process. Moreover, we discuss the state of art datasets and subsequent classification procedure. Also, a comparative study of some of the more popular depth-map approaches has provided in greater detail. The proposed methods are evaluated on three depth-based datasets “MSR Action 3D”, “MSR Hand Gesture”, and “MSR Daily Activity 3D”. Experimental results achieved 100%, 95.83%, and 96.55% respectively. While combining depth and color features on “RGBD-HuDaAct” Dataset, achieved 89.1%.
THE DETECTING OF ABNORMAL CROWD ACTIVITIES BASED ON MOTION VECTOR
基于运动矢量的异常群体行为检测
Optik - International Journal for Light and Electron Optics, In press, accepted manuscript, Available online 8 December 2017
Wei Yan, Zheng Zou, Jianbin Xie, Tong Liu, Peiqin Li
Abstract:Aiming at the crowd in high-definition video motion state of sudden changes in rapid detection of abnormal crowd behavior problem, this paper proposes a kind of abnormal behavior crowd detection method based on motion vector. This algorithm is established upon the Social Force Model, first, extracts the motion vector in the code stream of the high-definition compressed videos, computes the interaction force in the social force model and rapidly draws the characteristics of the moving crowd; then according to the algorithm, we perform the bag of words approach and histogram statistics on the intensity and angle of the interaction force flow; finally we analyze two histograms to distinguish the moving state of the crowd and fulfill the detection of the abnormal crowd movement. The simulation experiment shows the method compared with the traditional social force model, in the 1024 × 768HD video frame processing speed on the average increase of 30% in average, the discrimination of abnormal frame advance 35 frames, the recall to an average increase of 22%.
