Learn More
—Intuitively, instances of the same object category with different spatial scales may exhibit dramatically different features. Thus, large variance in instance scales, which results in undesirable large intra-category variance in features, may severely hurt the performance of modern object instance detection methods. We argue that this issue can be(More)
Modern deep neural network based object detection methods typically classify candidate proposals using their interior features. However, global and local surrounding contexts that are believed to be valuable for object detection are not fully exploited by existing methods yet. In this work, we take a step towards understanding what is a robust practice to(More)
Traditional total variation model leads to an undesirable staircase effect and is hard to eliminate high frequency noises in image restoration. In this paper, to solve this problem, a novel image restoration model based on adaptive total variation is proposed. A gradient fidelity term is coupled with adaptive total variation model. In order to choose proper(More)
During the process of moving object detection in an intelligent visual surveillance system, a scenario with complex background is sure to appear. The traditional methods, such as "frame difference" and "optical flow", may not able to deal with the problem very well. In such scenarios, we use a modified algorithm to do the background modeling work. In this(More)
In this paper, we propose a novel hierarchical framework that combines motion and feature information to implement infrared-visible video registration on nearly planar scenes. In contrast to previous approaches, which involve the direct use of feature matching to find the global homography, the framework adds coarse registration based on the motion vectors(More)
—Most of existing detection pipelines treat object proposals independently and predict bounding box locations and classification scores over them separately. However, the important semantic and spatial layout correlations among proposals are often ignored, which are actually useful for more accurate object detection. In this work, we propose a new EM-like(More)
In this letter, we present a novel visual tracking algorithm based on sparse representation. In contrast to just use the target templates and the trivial templates to sparsely represent the target, we propose to further constrain the model with a set of discriminative weight maps. These weight maps contain the reliable structures of the target object. They(More)
This paper proposes a novel tracking framework with adaptive features and constrained labels (AFCL) to handle illumination variation, occlusion and appearance changes caused by the variation of positions. The novel ensemble classifier, including the Forward-Backward error and the location constraint is applied, to get the precise coordinates of the(More)