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 paper, we use edge detection to get an edge difference image just to enhance the ability of resistance illumination variation. Then we use a “multi-block temporal-analyzing LBP (Local Binary Pattern)” algorithm to do the segmentation. In the end, a connected component is used to locate the object. We also produce a hardware platform, the core of which consists of the DSP (Digital Signal Processor) and FPGA (Field Programmable Gate Array) platforms and the high-precision intelligent holder.

Trackers based on fully-convolutional Siamese networks regard tracking as a process of learning a similarity function. By utilizing shallow networks and off-line training, Siamese trackers can achieve high tracking speed and perform well in some simple scenes. However, due to the less semantic information and the invariant template, Siamese trackers still have a gap compared with the state-of-the-art methods in complex scenes and other challenging problems (Occlusion, Deformation, etc.). In this paper, we propose a Siamese tracking algorithm with deep features and robust feature fusion (SiamDF). The improved ResNet-18 network is utilized to replace the traditional shallow network and extract the deep features with more semantic information. For eliminating the negative effect of padding and making better use of the deep network, the proposed algorithm adopts the spatial aware sampling strategy to overcome the strict translation invariance. Meanwhile, a final response map with high quality can be obtained by using the multi-layer feature fusion. Thus, the tracker can significantly reduce the impact of the distractors in complex scenes. In addition, an adaptive feature information fusion is adopted to update the template, so that the algorithm can adapt to various changes of the target appearance. Objective evaluation on the OTB100 dataset shows that the precision and the overlap success can reach 0.852 and 0.658 respectively. Moreover, the EAO value evaluated on the VOT2016 database can reach 0.336. These results demonstrate that our algorithm can effectively improve the tracking performance and perform favorably in both robustness and accuracy.

Existing Siamese network based trackers are easily disturbed by large deformation, occlusion and distractor objects in the background. By comparing these trackers, we observe that the monotonous positive pairs usually have limited challenging factors (Occlusion, Deformation, etc.), which may make the learned features less robust. In addition, the foreground information of the substantial training data is utilized directly without deeper exploration. Thus, the trackers cannot effectively discriminate the foreground from the semantic backgrounds. In this paper, we focus on modifying the Siamese tracker by enriching the positive pairs and taking further advantage of the foreground information. During the offline training phase, a simple sampling strategy is adopted to enrich the challenging factors in positive pairs, which can effectively enhance the robustness of the tracker. At the same time, we highlight the foreground information by padding the background, and the information is utilized to generate a novel padding loss, which guides the tracker to pay less attention to the distractors in the background. Moreover, an improved feature information fusion is adopted to update the template, so that the tracker can adapt to the drastic appearance changes. Comprehensive experiments on the OTB and the VOT benchmarks demonstrate that our proposed tracker can achieve outstanding performance in both accuracy and robustness.

An automatic colorization algorithm can convert a grayscale image to a colorful image using regression loss functions or classification loss functions. However, the regression loss function leads to brown results, while the classification loss function leads to the problem of color overflow and the computation of the color categories and balance weights of the ground truth required for the weighted classification loss is too large. In this paper, we propose a new method to compute color categories and balance the weights of color images. In this paper, we propose a new method to compute color categories and balance weights of color images. Furthermore, we propose a U-Net-based colorization network. First, we propose a category conversion module and a category balance module to obtain the color categories and to balance weights, which dramatically reduces the training time. Second, we construct a classification subnetwork to constrain the colorization network with category loss, which improves the colorization accuracy and saturation. Finally, we introduce an asymmetric feature fusion (AFF) module to fuse the multiscale features, which effectively prevents color overflow and improves the colorization effect. The experiments show that our colorization network has peak signal-to-noise ratio (PSNR) and structure similarity index measure (SSIM) metrics of 25.8803 and 0.9368, respectively, for the ImageNet dataset. As compared with existing algorithms, our algorithm produces colorful images with vivid colors, no significant color overflow, and higher saturation.

An 8×8 wavelength reconfigurable photonic switch is described using micro-ring resonators fabricated on silicon substrate. Switch channels are routed by independent thermo-optic tuning of resonators with local heaters. Device fabrication and characterization are presented.