Project Type: The project is the Crime Detection Module of ISDR IMPRINT Project
PI: Prof. Santos Kumar Das, Co-PI: Prof. Umesh Chandra Pati, and others
Abstract: The project focuses on the development of a system for video surveillance based automatic crime alert wherein the system is capable of analyzing and classifying crime related information based on captured data and shares the data through a cloud data center to an emergency network, which in turns attends the incident without any delay. Broadly, this complete project comprises of four sub-projects as follows.
Video Anomaly Detection
Abstract: The proposed model architecture comprises three major sections: spatial encoder, temporal encoder-decoder, and spatial decoder. The spatial encoder is implemented using three layers of the convolutional layers. Then, the temporal encoder-decoder is realized with the help of Convolutional Long Short Term Memory (ConvLSTM), gated with the tanh and sigmoid activation functions. Finally, the spatial decoder is implemented using three layers of deconvolutional layers. The proposed model has trained only on the normal classes dataset by minimizing the reconstruction error. Later, a high reconstruction error resulted when the trained model was tested using the test dataset susceptible to anomalous activities. Subsequently, a high anomaly score and low regularity score have resulted. When the regularity score of the frames falls below the set threshold level, then the corresponding frames are treated as anomalous ones. The proposed model is trained and tested on UCSD Ped1 and Ped2 dataset successfully. The results of the performance evaluation are found to be promising.
Anomalous Weapon Classification
Weapon Recognition
Anomalous Person Recognition
Duration: from 22nd Sept. 2017 to till date
Sponsoring Agency: IMPRINT India
Organization: NIT Rourkela.
Project Type: The project is the Crime Detection Module of ISDR IMPRINT Project
PI: Prof. Santos Kumar Das, Co-PI: Prof. Umesh Chandra Pati, and others
Abstract: There is a huge demand for video surveillance-based intelligent security systems that can automatically detect unauthorized entry or mal-intentional intrusion to unattended sensitive areas and notify the concerned authorities in real-time. A novel video-based Intrusion Detection System (IDS) using deep learning is proposed. Here, You Only Look Once (YOLO) algorithm is used for object detection and intrusion is decided using our proposed algorithm based on the shifted center of mass of the detected object. Further, Simple Online and Realtime Tracking (SORT) algorithm is used to track the intruder in real-time. The developed system is also implemented and tested for live video stream using NVIDIA Jetson TX2 development platform with an accuracy of 97% and average fps of 30. Here, the proposed IDS is a generic one where the user can select the region of interest (the area to be intrusion free) of any size and shape from the reference (starting) frame and potential intruders such as a person, vehicle, etc. from the list of trained object classes. Hence, it can have a wide range of smart city applications such as person intrusion-free zone, no vehicle entry zone, no parking zone, smart home security, etc.
Duration: from 22nd Sept. 2017 to till date
Sponsoring Agency: IMPRINT India
Organization: NIT Rourkela.
Smart Loitering Detection System using Multi-camera Video Surveillance Network
Project Type: The project is the Crime Detection Module of ISDR IMPRINT Project
PI: Prof. Santos Kumar Das, Co-PI: Prof. Umesh Chandra Pati, and others
Abstract: A deep-learning-based Loitering Detection System (LDS) with re-identification (ReID) capability over a multicamera network is proposed. The proposed LDS is mainly comprised of object detection and tracking, loitering detection, feature extraction, camera switching, and re-identification of the loiterer. The person is detected using You Only Look Once (YOLOv3) and tracked using Simple Online Real-time Tracking with a deep association matrix (DeepSORT). From the trajectory analysis, the person is treated as a loiterer once the time and displacements thresholds are satisfied. When the loiterer moves one camera to another, then the algorithm is switched to the appropriate camera feed as per the proposed camera switching algorithm to minimize the computational cost. Subsequently, the loiterer is reidentified in the switched camera feed by comparing the features of the loiterer extracted by the MobileNets with that of the other detected persons based on the triplet loss criteria. The proposed system provides an enhanced accuracy of 96 % on average fps of 33 (without ReID) and 81.5 % at average fps of 30 (with ReID).
Duration: from 22nd Sept. 2017 to till date
Sponsoring Agency: IMPRINT India
Organization: NIT Rourkela.