Effective detection of small targets plays a pivotal role in infrared (IR) search and track applications for modern military defense or attack. However, IR small targets are very difficult to detect because of their weak brightness, small size, and lack of shape, structure, texture, and other information elements. In order to simultaneously satisfy the robustness and timeliness of target detection, inspired by density peak clustering and the human visual system, an idea combining an improved density peak global search and local contrast calculation is proposed. First, the positions of candidate targets are determined in the preprocessed image using the improved density peak global search method (IDPGSM). Second, the saliency map is obtained using the double-weights enhanced local contrast method (DWELCM) for the candidate target neighborhood. Finally, adaptive threshold segmentation is used to detect IR small targets. Through comprehensive analysis of five evaluation indicators, the experimental results on seven real sequences and three hundred IR images of different scenes that the proposed method has better detection performance compared with six baseline methods. It can quickly and accurately determine the small target position in the case of severe background clutter and noise interference. Index Terms-Double-weights enhanced local contrast method (DWELCM), improved density peaks global search (IDPGSM), infrared (IR) small target, three-layer window. I. INTRODUCTIONA N INFRARED (IR) detection system is a passive detection device that works in the IR spectrum of the atmospheric window band. It is an important part of advanced electronic warfare and integrated fire-control systems. In a complex and strong electromagnetic interference environment, an IR detection system has many advantages, such as strong anti-interference ability, good concealment, ability to work during the day and night, and high measurement accuracy. Therefore, it is widely used in weapon systems for IR early warning, reconnaissance, and precision guidance in airborne, shipborne, vehicle, and spaceborne applications [1]. In a complex battlefield environment, an IR detection system is often required to quickly locate and Manuscript

No abstract

Ship detection is one of the fundamental tasks in computer vision. In recent years, the methods based on convolutional neural networks have made great progress. However, improvement of ship detection in aerial images is limited by large-scale variation, aspect ratio, and dense distribution. In this paper, a Critical and Align Feature Constructing Network (CAFC-Net) which is an end-to-end single-stage rotation detector is proposed to improve ship detection accuracy. The framework is formed by three modules: a Biased Attention Module (BAM), a Feature Alignment Module (FAM), and a Distinctive Detection Module (DDM). Specifically, the BAM extracts biased critical features for classification and regression. With the extracted biased regression features, the FAM generates high-quality anchor boxes. Through a novel Alignment Convolution, convolutional features can be aligned according to anchor boxes. The DDM produces orientation-sensitive feature and reconstructs orientation-invariant features to alleviate inconsistency between classification and localization accuracy. Extensive experiments on two remote sensing datasets HRS2016 and self-built ship datasets show the state-of-the-art performance of our detector.

With the recent development of deep convolutional neural network (CNN), remote sensing for ship detection methods has achieved enormous progress. However, current methods focus on the whole ships and fail on the component’s detection of a ship. To detect ships from remote-sensing images in a more refined way, we employ the inherent relationship between ships and their critical parts to establish a multilevel structure and propose a novel framework to improve the performance in identifying the multilevel objects. Our framework, named the dual detector network (DD-Net), consists of two carefully designed detectors, one for ships (the ship detector) and the other for their critical parts (the critical part detector), for detecting the critical parts in a coarse-to-fine manner. The ship detector offers detection results of the ship, based on which the critical part detector detects small critical parts inside each ship region. The framework is trained in an end-to-end way by optimizing the multitask loss. Due to the lack of publicly available datasets for critical part detection, we build a new dataset named RS-Ship with 1015 remote-sensing images and 2856 annotations. Experiments on the HRSC2016 dataset and the RS-Ship dataset show that our method performs well in the detection of ships and critical parts.