Moving Object Detection
Moving Object Detection In this project, we will dive deeper and look at various algorithms that can be used for moving object detection using raspberry pi and OpenCV. We will start with the algorithms belonging to the RCNN family, i.e. RCNN, Fast RCNN, and Faster RCNN. In the upcoming article of this series, we will cover more advanced algorithms like Mobile net, SSD, etc. For this approach, the automatic classifier NN can be used for classification based on learning with some training samples of that category. This network uses the tangent sigmoid function as the kernel function. Finally, the simulated result shows that a used network classifier provides minimum error during training and better accuracy in classification.
The algorithm applies a neural network to an entire image. The network divides the image into an S x S grid and comes up with bounding boxes, which are boxes drawn around images and predicted probabilities for each of these regions.
The method used to come up with these probabilities is logistic regression. The bounding boxes are weighted by the associated probabilities. For class prediction, independent logistic classifiers are used.
In this article, I am going to demonstrate how to implement the YOLO algorithm with a pre-trained model. First, we would need to install DarkNet. DarkNet is a neural network framework that is open source.
- Edge detection
- Morphological filters
- SVM classification
- Not a real-time application
- Information about objects is very less
- The accuracy of output is less
- Caffe model data set(Darknet)
- Deep learning classification
- Blob detection
- Maximum accuracy in classification
- Real-time achievement
- Machine-based prediction
- Accuracy of output is increased
- Commercial applications
- Forensic lab
- Face recognition
HARDWARE BLOCK DIAGRAM
- Raspberry pi
- Raspberry pi OS
- Python IDE
- OpenCV library
 X. Wu, D. Hong, J. Chanussot, Y. Xu, R. Tao, and Y. Wang, ??Fourier-based rotation-invariant feature boosting: An efficient framework for geospatial object detection,?? IEEE Geosci. Remote Sens. Lett., vol. 17, no. 2, pp. 302?306, Feb. 2020.
 X. Wu, D. Hong, J. Tian, J. Chanussot, W. Li, and R. Tao, ??ORSIm detector: A novel object detection framework in optical remote sensing imagery using spatial-frequency channel features,?? IEEE Trans. Geosci. Remote Sens., vol. 57, no. 7, pp. 5146?5158, Jul. 2019.
? S. Ren, K. He, R. Girshick, and J. Sun, ??Faster R-CNN: Towards real-time object detection with region proposal networks,?? IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, pp. 1137?1149, Jun. 2017.
 Y. Li, S. Li, C. Chen, A. Hao, and H. Qin, ??Accurate and robust video saliency detection via self-paced diffusion,?? IEEE Trans. Multimedia, vol. 22, no. 5, pp. 1153?1167, May 2020.
? K. Kang, W. Ouyang, H. Li, and X. Wang, ??Object detection from video tubeless with convolutional neural networks,?? in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CPR), Jun. 2016, pp. 817? 825.
 C. Feichtenhofer, A. Pinz, and A. Zisserman, ??Detect to track and track to detect,?? in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2017, pp. 3057?3065.
 C. Chen, G. Wang, C. Peng, X. Zhang, and H. Qin, ??Improved robust video saliency detection based on long-term spatial-temporal information,?? IEEE Trans. Image Process., vol. 29, pp. 1090? 1100, 2020.