Neural Networks has become one of the most demanded areas of Information Technology and it has been successfully applied to solving many issues of Artificial Intelligence, for example, speech recognition, computer vision, natural language processing, and data visualization. This thesis describes the developing the neural network model for object detection and tracking. With the progress of science and technology, information technology was advancing rapidly. The understanding of moving object based on vision has also developed rapidly. Its related technologies have been widely used in public transportation, square, government, bank and other scenes. At present, there are commonly used algorithms in moving object detection, including the difference method (background difference method and time difference method) and optical flow method and neural network. The difference method was based on the current video and the reference image subtraction to complete the detection. Some practical details for creating the Neural Network and image recognition in the Caffe Framework are given as well.

Detection of moving objects; tracking of moving objects; behavior understanding, Neural Network, Caffe model, CNN

[1] J. Redmon, S. Divvala, R. Girshick and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” IEEE CVPR, May 2016.
[2] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, A. C. Berg, “SSD: Single Shot Multi-Box Detector,” https://arxiv.org/abs/1512.02325.
[3] S. Ren, K. He, R. Girshick and J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE CVPR, Jan 2016.
[4] “Convolutional Neural Networks (LeNet),” Deeplearning.net, 2008. [Online]. Available: http://deeplearning.net/tutorial/lenet.html.
[5] Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, “Gradient-based Learning Applied to Document Recognition,” Proceedings of the IEEE, 1998.
[6] D. Erhan, C. Szegedy, A. Toshev and D. Anguelov, “Scale Object Detection Using Deep Neural Networks,” IEEE International Conference on Computer Vision and Pattern Recognition, 2014.
[7] Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, T. Darrell, “Caffe: Convolutional Architecture for Fast Feature Embedding,” BVLC, 2014. [Online]. Available: http://caffe.berkeleyvision.org/.
[8] K. Simonyan, A. Zisserman, “Very deep Convolutional networks for large-scale image recognition,” International Conference on Learning Representations, Apr 2015.
[9] Tekalp AM, Digital video processing. Prentice Hall, 1995, New Jersey. B.N. Subudhi, S Ghosh , P.K. Nanda and A. Ghosh, “Moving object detection using spatio-temporal multilayer compound Markov Random Field and histogram thresholding based change detection”, Multimedia Tools and Applications, vol. 76(11), June 2017, pp. 13511–13543.
[10] Shiqi Yu, Sen Jia and Chunyan Xu, “Convolutional neural networks for hyper spectral image classification”, Neuro-computing, vol. 219, Jan.2017, pp. 88-98.
[11] Tianming Liang, Xinzheng Xu and Pengcheng Xiao, “A new image classification method based on modified condensed nearest neighbor and Convolutional neural networks”, Pattern Recognition Letters, vol. 94, July 2017, pp-105-111.
[12] X.X. Niu and C.Y. Suen, “A novel hybrid CNN–SVM classifier for recognizing handwritten digits”, Pattern Recognition, vol. 45, 2012, pp. 1318-1325.
[13] Deepak Kumar Panda; Sukadev Meher, “Detection of Moving Objects Using Fuzzy Color Difference Histogram Based Background Subtraction”, IEEE Signal Processing Letters, Vol.23, No.1, pp.45-49, 2016.
[14] NingLi, TongweiLu, Yanduo Zhang. Object tracking algorithm based on the color histogram probability distribution. International Conference on Graphic and Image Processing, 2018.
[15] Fu Sun, JianXin Song. Research on Parallel Particle Filtering Target Tracking Algorithm Based on Hadoop. 2015 5th International Conference on Computer Sciences and Automation Engineering (ICCSAE 2015), 2016.
[16] Fan, J., W. Xu, Y. Wu, and Y. Gong, “Human tracking using convolutional neural networks”, IEEE Transactions on Neural Networks 21(10), 1610-1623, 2010.
[17] Hong, S., T. You, S. Kwak, and B. Han, “Online tracking by learning discriminative saliency map with convolutional neural network”, arXiv preprint arXiv: 1502.06796.
[18] Wang, N., S. Li, A. Gupta, and D. Yeung, “Transferring rich feature hierarchies for robust visual tracking”, Computing Research Repository abs/1501.04587, 2015.
[19] Wang N., S. Li, A. Gupta, and D. Yeung, “Transferring rich feature hierarchies for robust visual tracking”. Computing Research Repository 2015, abs/1501.04587.