Metallic surface defect detection is critical to ensure the quality of industrial products. Recently, human-advanced surface defect detection algorithms have been proposed. Most of these algorithms rely on convolutional neural networks (CNN) and an anchoring scheme. However, a convolution unit only samples the input feature maps at fixed shapes and locations. Similarly, a set of anchors are uniformly predefined with fixed scales and shapes, which increases the difficulties of bounding box regression. Therefore, we propose an adaptive convolution and anchor network for metallic surface defect detection, named ACA-Net. Specifically, an adaptive convolution and anchor (ACA) module is proposed, which mainly consists of adaptive convolution and an adaptive anchor. Firstly, an adaptive convolution module (ACM) is designed, which adaptively determines the location and shape of each convolution unit. In addition, a multi-scale feature adaptive fusion (MFAF) is proposed, which is used in ACM to extract and integrate multi-scale features. Then, an adaptive anchor module (AAM) is proposed to yield more suitable anchor boxes by adaptively adjusting shapes. Extensive experiments on NEU-DET dataset and GC10 dataset validate the performance of the proposed approach. ACA-Net achieves 1.8% on NEU-DET dataset higher Average Precision (AP) than GA-RetinaNet. Furthermore, the proposed ACA module is also adopted in GA-Faster R-CNN, improving the AP by 1.2% on NEU-DET dataset.

Text categorization is the process of assigning documents to a set of previously fixed categories. In this paper we develop an optimal SVM algorithm for text classification via multiple optimal strategies, such as a novel importance weight definition, the feature selection using the likelihood ratio for binomial distribution, the optimal parameter settings, etc. Comparison between our method and other conventional text classification algorithms is conducted on Reuter and TREC corpora. The experimental results indicate that our proposed algorithm yields much better performance than other conventional algorithms

Object tracking is aimed at tracking a given target that is only specified in the first frame. Due to the rapid movement and the interference of cluttered backgrounds, object tracking is a significant challenging issue in computer vision. This research put forward an innovative feature pyramid and optical flow estimation based on the Siamese network for object tracking, which is called SiamFP. The SiamFP jointly trains the optical flow and the tracking task under the Siamese network framework. We employ the optical flow network based on the pyramid correlation mapping to evaluate the movement information of the target in two contiguous frames, to increase the accuracy of the feature representation. Simultaneously, we adopt spatial attention as well as channel attention to effectively restrain the ambient noise, stress the target area, and better extract the features of the given object, so that the tracking algorithm has a higher success rate. The proposed SiamFP obtains state-of-the-art performance on OTB50, OTB2015, and VOT2016 benchmarks while exhibiting better real-time and robustness.

Benefiting from the powerful feature representation ability of deep learning, Convolutional Neural Network (CNN) provides a better solution to estimate accurately the number of people in a crowded scene, but it still faces many problems that need to be solved urgently. It is one of the key and difficult points in the field to reduce the complexity of the network and to improve the real-time performance of the network, so as to improve the accuracy of crowd counting. Firstly, this paper introduces the research background and application of crowd counting. Secondly, it focuses on the commonly used counting model, loss function, and dataset and evaluation method. Then compare the performance structure, advantages and disadvantages of different algorithms horizontally on several published datasets. Finally, it summarizes the shortcomings of the existing crowd counting, put forward to the future research direction of crowd counting.

The paper proposes a novel graphic interface design for image-based rescue robot systems. The whole window is used to display collected disaster images. Functional fields, which are parts of image itself, are specified for navigating operations. Functional fields have unbodied appearances. With the proposed design, the area cost of the image window and the human attention shift outside images are reduced to zero. Experiment results by simulation and a physical system show that the proposed interface design is more efficient than conventional interface design in navigating a remotely controlled tank rescue robot.