Fuzzy system based human behavior recognition by combining behavior prediction and recognition

基于结合行为预测与识别模糊系统的人类行为识别

Expert Systems with Applications, Volume 81, 15 September 2017, Pages 108-133

Ganbayar Batchuluun, Jong Hyun Kim, Hyung Gil Hong, Jin Kyu Kang, Kang Ryoung Park

Abstract:With the development of intelligent surveillance systems, human behavior recognition has been extensively researched. Most of the previous methods recognized human behavior based on spatial and temporal features from (current) input image sequences, without the behavior prediction from previously recognized behaviors. Considering an example of behavior prediction,“punching”is more probable in the current frame when the previous behavior is“standing”as compared to the previous behavior being“lying down.”Nevertheless, there has been little study regarding the combination of currently recognized behavior information with behavior prediction. Therefore, we propose a fuzzy system based behavior recognition technique by combining both behavior prediction and recognition. To perform behavior recognition during daytime and nighttime, a dual camera system of visible light and thermal (far infrared light) cameras is used to capture 12 datasets including 11 different human behaviors in various surveillance environments. Experimental results along with the collected datasets and open database showed that the proposed method achieved higher accuracy of behavior recognition when compared to conventional methods.

Toward an audiovisual attention model for multimodal video content

多模式视频内容的音视频注意力模型

Neurocomputing, Volume 259, 11 October 2017, Pages 94-111

Naty Sidaty, Mohamed-Chaker Larabi, Abdelhakim Saadane

Abstract:Visual attention modeling is a very active research field and several image and video attention models have been proposed during the last decade. However, despite the conclusions drawn from various studies about the influence of human gazes by the presence of sound, most of the classical video attention models do not account for the multimodal nature of video (visual and auditory cues). In this paper,we propose an audiovisual saliency model with the aim to predict human gaze maps when exploring video content. The model, intended for videoconferencing, is based on the fusion of spatial, temporal and auditory attentional maps. Based on a real-time audiovisual speaker localization approach, the proposed auditory map is modulated depending of the nature of faces in the video, i.e. speaker or auditor. State-of-the-art performance measures have been used to compare the predicted saliency maps with the eye-tracking ground truth. The obtained results show the very good performance of the proposed model and a significant improvement compared to non-audio models.

Pedestrian abnormal event detection based on multi-feature fusion in traffic video

基于多特征融合的交通视频行人异常事件探测

Optik - International Journal for Light and Electron Optics, Volume 154, February 2018, Pages 22-32

Xuan Wang, Huansheng Song, Hua Cui

Abstract: Pedestrian abnormal event detection is an active research area to improve traffic safety for intelligent transportation systems (ITS). This paper proposes an efficient method to automatically detect and track far-away pedestrians in traffic video to determine the abnormal behavior events. Firstly, pedestrian features are extracted by the multi-feature fusion method. Then, the similar features in current frame of all candidate objects are matched with the characteristic information of pedestrians in the previous frame which is considered as a template. Finally, pedestrian trajectory analysis algorithms are employed on the tracking trajectories and the motion information is attained, which can realize the early classification warning of pedestrian events. Experimental results on different traffic scenes in practice demonstrate that this method has good robustness in complex traffic. Moreover, the proposed method performs better compared with some other methods.

Video Anomaly Detection in Confined Areas

封闭（受限）区域视频异常探测

Procedia Computer Science, Volume 115, 2017, Pages 448-459

Emmanu Varghese, Jaison Mulerikkal, Amitha Mathew

Abstract:This paper proposes a new supervised algorithm for detecting abnormal events in confined areas like ATM room, server room etc. In the training phase, algorithm learns the motion path and speed of objects in the video. In the testing phase, if any motion happens other than in the learned motion path or the speed of object has large variation from the learned speed then the algorithm alert it as abnormal event. The proposed method process video in groups of frames. The algorithm uses statistical functions to learn the motion path and speed of objects in a video.