Modeling Abandoned Object Detection And Recognition In Real-Time Surveillance
|International Journal of Engineering Trends and Technology (IJETT)||
|© 2021 by IJETT Journal|
|Year of Publication : 2021|
|Authors : WWWWTWKMRNDB Weliwita, JAP Isuru, SC Premaratne
|DOI : 10.14445/22315381/IJETT-V69I2P226|
MLA Style: WWWWTWKMRNDB Weliwita, JAP Isuru, SC Premaratne "Modeling Abandoned Object Detection And Recognition In Real-Time Surveillance" International Journal of Engineering Trends and Technology 69.2(2021):188-193.
APA Style:WWWWTWKMRNDB Weliwita, JAP Isuru, SC Premaratne. Modeling Abandoned Object Detection And Recognition In Real-Time Surveillance. International Journal of Engineering Trends and Technology, 69(2), 188-193.
This paper presents the model`s accuracy of abandoned object detection and recognition in real-time surveillance. There basically focused three models call Faster Region Convolutional Neural Network (Faster RCNN), Single Shot Multiple Detector (SSD), and You Only Look Once Version 3 (YOLO-Version 3). The research tested under MXnet Framework used the GluonCV Library for object detection, OpenCV used for pre-processing, and other preliminary adjustments of captured video inputs in the Python 3.8 Platform. The objectives of the research listed as acquiring knowledge on abandoned object detection, algorithms, different frameworks, and neural network. Identifying significant parameters, determining accuracy performances of the different models, and finalizing the most accurate model in real-time recognition and detection of an object. The research focused on the use of practical readings and calculation of the accuracy from ‘Confution Matrix.’ It suffices to obtain the maximum accurate results of each model separately. Python program used to obtain the input videos to decide the abundancy very sensitively. Then those reading tested and received the results with percentage value to decide the accuracy. Finally, the Confusion Matrix could be able to provide the results separately. Those results revealed that YOLO-V3 gave the most accurate results; secondly, SSD and third place goes to Faster RCNN.
 Rohith Sri Sai, M., S. Rella, and S. Veeravalli, OBJECT DETECTION AND IDENTIFICATION A Project Report. (2019).
 Tripathi, R.K., A.S. Jalal, and C. Bhatnagar. A framework for abandoned object detection from video surveillance. in 2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG). (2013). IEEE.
 Girshick, R., et al. Rich feature hierarchies for accurate object detection and semantic segmentation. in Proceedings of the IEEE conference on computer vision and pattern recognition. (2014).
 Girshick, R., et al., Region-based convolutional networks for accurate object detection and segmentation. IEEE transactions on pattern analysis and machine intelligence, 38(1)(2015) 142-158.
 Krizhevsky, A., I. Sutskever, and G.E. Hinton, Imagenet classification with deep convolutional neural networks. Communications of the ACM, 2017. 60(6)(2017) 84-90.
 Long, J., E. Shelhamer, and T. Darrell. Fully convolutional networks for semantic segmentation. in Proceedings of the IEEE conference on computer vision and pattern recognition. (2015).
 Toshev, A. and C. Szegedy. Deeppose: Human pose estimation via deep neural networks. in Proceedings of the IEEE conference on computer vision and pattern recognition. (2014).
 Lin, K. et al., Abandoned object detection via temporal consistency modeling and back-tracing verification for visual surveillance. IEEE Transactions on Information Forensics and Security, 10(7)(2015) 1359-1370.
 Liao, W., et al., Security event recognition for visual surveillance. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 4 (2017), Nr. 1W1, 4(1W1)(2017) 19-26.
 Gupta, A., et al. Real-Time Abandoned Object Detection Using Video Surveillance. in Proceedings of the International Conference on Recent Cognizance in Wireless Communication & Image Processing. (2016) Springer.
 Fan, Q. and S. Pankanti. Modeling of temporarily static objects for robust abandoned object detection in urban surveillance. in 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). (2011) IEEE.
 Zeng, Y. et al., A novel abandoned object detection system based on three-dimensional image information. Sensors, 15(3)(2015) 6885-6904.
 Fan, Q. and S. Pankanti. Robust foreground and abandonment analysis for large-scale abandoned object detection in complex surveillance videos. in 2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance. (2012) IEEE.
 Fu, H., et al. Abandoned object detection in highway scene. in 6th International Conference on Pervasive Computing and Applications. (2011) IEEE.
Faster RCNN, SSD, YOLO-V3, MXnet, GluonCV, OpenCV, and Python 3.8.