Due to the long training time and large memory consumption of R-CNNs, a fast R-CNN was proposed. SPPNet proposed spatial pyramid pooling, so that the size of the image no longer limited the input of the CNN, which also improved the recognition performance for multi-scale targets.
After AlexNet proposed a deep convolutional neural network for image classification to achieve a breakthrough in performance, many CNN-based methods of object detection began to emerge. The experimental results demonstrated that our method could improve the performance of real-world pedestrian and vehicle detection.Īs we all know, object detection is based on image classification. At the same time, we provided many useful strategies to improve the detector. As a result, we improved the detector performance with single-class object detection for pedestrians and vehicles, respectively. We also found that pedestrians and vehicles were separable in size and comprised more than one target type. At the same time, we used varifocal loss to solve the imbalance between positive and negative samples caused by the high resolution. When fusing the sub-images, we proposed a midline method to reduce the cropped objects that NMS could not eliminate. In order to improve the performance of existing pedestrian and vehicle detectors in real-world scenarios, we used a sliding window to crop the original images to solve this problem. Although existing pedestrian and vehicle detection algorithms have achieved remarkable success for standard images, their methods are not suitable for ultra-high-resolution images. The large field of view and high resolution provide global and local information, which enables object detection in real-world scenarios. Recently, with the development of gigacameras, gigapixel-level images have emerged. Pedestrian and vehicle detection is widely used in intelligent assisted driving, pedestrian counting, drone aerial photography, and other applications.
0 kommentar(er)
