Li, Y., et al.: Yolov3-lite: a lightweight crack detection network for aircraft structure based on depthwise separable convolutions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. Lin, T., et al.: Focal loss for dense object detection. Springer International Publishing, Cham (2016). (eds.) Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I, pp. In: Leibe, B., Matas, J., Sebe, N., Welling, M. Liu, W., et al.: SSD: single shot multibox detector. Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. 779–788 (2016)īochkovskiy, A., Wang, C., Liao, H.M.: Yolov4: Optimal Speed and Accuracy of Object Detection. Redmon, J., et al.: You only look once: unified, real-time object detection. Lin, T., et al.: Feature pyramid networks for object detection. Ren, S., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. 1440–1448 (2015)įaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. He, K., Zhang, X., Ren, S., et al.: Spatial pyramid pooling in deep convolutional networks for visual recognition. Rich feature hierarchies for accurate object detection and semantic segmentation. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition: IEEE, pp. 1–8 (2008)įelzenszwalb, P.F., Girshick, R.B., McAllester, D.: Cascade object detection with deformable part models. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition: IEEE, pp. 32(9), 1627–1645 (2009)įelzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. 886–893 (2005)įelzenszwalb, P.F., et al.: Object detection with discriminatively trained part-based models. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (cvpr'05): IEEE, pp. 38(1), 142–158 (2015)ĭalal, N., Triggs, B.: Histograms of oriented gradients for human detection. Girshick, R., et al.: Region-based convolutional networks for accurate object detection and segmentation. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. The improved YOLO model can also obtain a larger batch size with the same image size, providing an excellent solution for training models on hardware-constrained devices. While getting a 4-fold FPS improvement, the network model parameters remain essentially unchanged, and the computational effort becomes a quarter of that of the original network. The Slice-Concat structure proposed in this paper does not require too many changes to YOLOv3 and YOLOv3-SPP, and the four times improvement in detection speed is obtained only by changing the width and height of the input feature map. So reducing the model size and increasing the model detection speed becomes a trendy research topic. Due to the limitation of mobile devices, the size of object detection models is limited, and it is not easy to achieve the ideal balance between detection accuracy and detection speed. Object detection is an exciting research area in computer vision, widely used in autonomous driving, face recognition, and drones.
0 Comments
Leave a Reply. |