This paper mainly studies the berthing ship target detection method of overhead-view image under the condition of a few training samples. Because of the limited training samples, we use the complete data set unrelated to the target detection task for pre-training to obtain a classification model, then expand the data according to a certain percentage and finally complete the training of the target detection model. This paper uses the idea of segmentation to solve the target detection problem. We adjusted the configuration of the region proposal network including the size of anchor frame and the threshold of non-maximum suppression according to the target morphology, so that the network generates a more accurate region of interest. Finally, the confidence levels, bounding-boxes and image masks of multi-objective generated concurrently. We performed experiments on self-made data sets which labeled from NWPU VHR-10 and produced good results, which proved the feasibility of this method in target detection of berthing ship target.
We proposed a saliency based algorithm to detect the ground mobile targets, such as plane and vehicle, in the images. The algorithm combines the bottom-up and top-down mode to detect the targets. Firstly, in the bottom-up mode, the algorithm extracts the low level image features, such as intensity, standard deviation and Gabor features, to calculate the difference between the current pixel and the pixel around it and use the difference as the bottom-up saliency of the pixel; Then, the algorithm extracts the HOG features of the plane and vehicle targets to train a SVM classifier, which can learn the high level knowledge of the target. When testing on a new image, the classifier uses the knowledge to predict the possibility of appearance of the target as the top-down saliency of each position of the image; Finally, we combine the two saliency maps to get the final saliency map and use it to detect targets in the image. Experiments show that the algorithm can effectively detect the ground mobile targets robustly in complex backgrounds.
Numerous tracking-by-detection methods have been proposed for robust visual tracking, among which compressive tracking (CT) has obtained some promising results. A scale-adaptive CT method based on multifeature integration is presented to improve the robustness and accuracy of CT. We introduce a keypoint-based model to achieve the accurate scale estimation, which can additionally give a prior location of the target. Furthermore, by the high efficiency of data-independent random projection matrix, multiple features are integrated into an effective appearance model to construct the naïve Bayes classifier. At last, an adaptive update scheme is proposed to update the classifier conservatively. Experiments on various challenging sequences demonstrate substantial improvements by our proposed tracker over CT and other state-of-the-art trackers in terms of dealing with scale variation, abrupt motion, deformation, and illumination changes.