Search Results (6)

The intelligent inspection of power lines and other difficult-to-access structures and facilities has been greatly enhanced by the use of Unmanned Aerial Vehicles (UAVs), which allow inspection in a safe, efficient, and high-quality fashion. This paper analyzes the characteristics of a scene containing power equipment and the operation mode of UAVs. A low-cost virtual scene is created, and a training sample for the power-line components is generated quickly. Taking a vibration-damper as the main object, an assembled detector based on geometrical constraint (ADGC) is proposed and is used to analyze the virtual dataset. The geometric positional relationship is used as the constraint, and the Faster Region with Convolutional Neural Network (R-CNN), Deformable Part Model (DPM), and Haar cascade classifiers are combined, which allows the features of different classifiers, such as contour, shape, and texture to be fully used. By combining the characteristics of virtual data and real data using UAV images, the power components are detected by the ADGC. The result produced by the detector with relatively good performance can help expand the training set and achieve a better detection model. Moreover, this method can be smoothly transferred to other power-line facilities and other power-line scenarios. Full article

Offshore and inland river ship detection has been studied on both synthetic aperture radar (SAR) and optical remote sensing imagery. However, the classic ship detection methods based on SAR images can cause a high false alarm ratio and be influenced by the sea surface model, especially on inland rivers and in offshore areas. The classic detection methods based on optical images do not perform well on small and gathering ships. This paper adopts the idea of deep networks and presents a fast regional-based convolutional neural network (R-CNN) method to detect ships from high-resolution remote sensing imagery. First, we choose GaoFen-2 optical remote sensing images with a resolution of 1 m and preprocess the images with a support vector machine (SVM) to divide the large detection area into small regions of interest (ROI) that may contain ships. Then, we apply ship detection algorithms based on a region-based convolutional neural network (R-CNN) on ROI images. To improve the detection result of small and gathering ships, we adopt an effective target detection framework, Faster-RCNN, and improve the structure of its original convolutional neural network (CNN), VGG16, by using multiresolution convolutional features and performing ROI pooling on a larger feature map in a region proposal network (RPN). Finally, we compare the most effective classic ship detection method, the deformable part model (DPM), another two widely used target detection frameworks, the single shot multibox detector (SSD) and YOLOv2, the original VGG16-based Faster-RCNN, and our improved Faster-RCNN. Experimental results show that our improved Faster-RCNN method achieves a higher recall and accuracy for small ships and gathering ships. Therefore, it provides a very effective method for offshore and inland river ship detection based on high-resolution remote sensing imagery. Full article

Visual-based vehicle detection has been studied extensively, however there are great challenges in certain settings. To solve this problem, this paper proposes a probabilistic framework combining a scene model with a pattern recognition method for vehicle detection by a stationary camera. A semisupervised viewpoint inference method is proposed in which five viewpoints are defined. For a specific monitoring scene, the vehicle motion pattern corresponding to road structures is obtained by using trajectory clustering through an offline procedure. Then, the possible vehicle location and the probability distribution around the viewpoint in a fixed location are calculated. For each viewpoint, the vehicle model described by a deformable part model (DPM) and a conditional random field (CRF) is learned. Scores of root and parts and their spatial configuration generated by the DPM are used to learn the CRF model. The occlusion states of vehicles are defined based on the visibility of their parts and considered as latent variables in the CRF. In the online procedure, the output of the CRF, which is considered as an adjusted vehicle detection result compared with the DPM, is combined with the probability of the apparent viewpoint in a location to give the final vehicle detection result. Quantitative experiments under a variety of traffic conditions have been contrasted to test our method. The experimental results illustrate that our method performs well and is able to deal with various vehicle viewpoints and shapes effectively. In particular, our approach performs well in complex traffic conditions with vehicle occlusion. Full article

Partially occluded object detection (POOD) has been an important task for both civil and military applications that use high-resolution remote sensing images (HR-RSIs). This topic is very challenging due to the limited object evidence for detection. Recent partial configuration model (PCM) based methods deal with occlusion yet suffer from the problems of massive manual annotation, separate parameter learning, and low training and detection efficiency. To tackle this, a unified PCM framework (UniPCM) is proposed in this paper. The proposed UniPCM adopts a part sharing mechanism which directly shares the root and part filters of a deformable part-based model (DPM) among different partial configurations. It largely reduces the convolution overhead during both training and detection. In UniPCM, a novel DPM deformation deviation method is proposed for spatial interrelationship estimation of PCM, and a unified weights learning method is presented to simultaneously obtain the weights of elements within each partial configuration and the weights between partial configurations. Experiments on three HR-RSI datasets show that the proposed UniPCM method achieves a much higher training and detection efficiency for POOD compared with state-of-the-art PCM-based methods, while maintaining a comparable detection accuracy. UniPCM obtains a training speedup of maximal 10× and 2.5× for airplane and ship, and a detection speedup of maximal 7.2×, 4.1× and 2.5× on three test sets, respectively. Full article

The goal of this research work is to improve the accuracy of human pose estimation using the Deformation Part Model (DPM) without increasing computational complexity. First, the proposed method seeks to improve pose estimation accuracy by adding the depth channel to DPM, which was formerly defined based only on red–green–blue (RGB) channels, in order to obtain a four-dimensional DPM (4D-DPM). In addition, computational complexity can be controlled by reducing the number of joints by taking it into account in a reduced 4D-DPM. Finally, complete solutions are obtained by solving the omitted joints by using inverse kinematics models. In this context, the main goal of this paper is to analyze the effect on pose estimation timing cost when using dual quaternions to solve the inverse kinematics. Full article

With the rapid development of optical remote sensing satellites, ship detection and identification based on large-scale remote sensing images has become a significant maritime research topic. Compared with traditional ocean-going vessel detection, inshore ship detection has received increasing attention in harbor dynamic surveillance and maritime management. However, because the harbor environment is complex, gray information and texture features between docked ships and their connected dock regions are indistinguishable, most of the popular detection methods are limited by their calculation efficiency and detection accuracy. In this paper, a novel hierarchical method that combines an efficient candidate scanning strategy and an accurate candidate identification mixture model is presented for inshore ship detection in complex harbor areas. First, in the candidate region extraction phase, an omnidirectional intersected two-dimension scanning (OITDS) strategy is designed to rapidly extract candidate regions from the land-water segmented images. In the candidate region identification phase, a decision mixture model (DMM) is proposed to identify real ships from candidate objects. Specifically, to improve the robustness regarding the diversity of ships, a deformable part model (DPM) was employed to train a key part sub-model and a whole ship sub-model. Furthermore, to improve the identification accuracy, a surrounding correlation context sub-model is built. Finally, to increase the accuracy of candidate region identification, these three sub-models are integrated into the proposed DMM. Experiments were performed on numerous large-scale harbor remote sensing images, and the results showed that the proposed method has high detection accuracy and rapid computational efficiency. Full article