Targeting at depicting land covers with pixelwise semantic categories, semantic segmentation in remote sensing images needs to portray diverse distributions over vast geographical locations, which is difficult to be achieved by the homogeneous pixelwise forward paths in the architectures of existing deep models. Although specific algorithms have been designed to select pixelwise adaptive forward paths for natural image analysis, it still lacks theoretical supports on how to obtain optimal selections. In this article, we provide mathematical analyses in terms of the parameter optimization, which guides us to design a method called hidden path selection network (HPS-Net). With the help of hidden variables deriving from an extra mini-branch, HPS-Net is able to tackle the inherent problem about inaccessible global optimums by adjusting the direct relationships between feature maps and pixelwise path selections in existing algorithms, which we call hidden path selection. For the better training and evaluation, we further refine and expand the 5-class Gaofen image dataset (GID-5) to a new one with 15 land-cover categories, i.e., GID-15. The experimental results on both GID-5 and GID-15 demonstrate that the proposed modules can stably improve the performance of different deep structures, which validates the proposed mathematical analyses.

This paper presents a new deep-learning based method to simultaneously calibrate the intrinsic parameters of fisheye lens and rectify the distorted images. Assuming that the distorted lines generated by fisheye projection should be straight after rectification, we propose a novel deep neural network to impose explicit geometry constraints onto processes of the fisheye lens calibration and the distorted image rectification. In addition, considering the nonlinearity of distortion distribution in fisheye images, the proposed network fully exploits multi-scale perception to equalize the rectification effects on the whole image. To train and evaluate the proposed model, we also create a new large-scale dataset labeled with corresponding distortion parameters and well-annotated distorted lines. Compared with the state-of-the-art methods, our model achieves the best published rectification quality and the most accurate estimation of distortion parameters on a large set of synthetic and real fisheye images.

Junctions play an important role in characterizing local geometrical structures of images, and the detection of which is a longstanding but challenging task. Existing junction detectors usually focus on identifying the location and orientations of junction branches while ignoring their scales, which, however, contain rich geometries of images. This paper presents a novel approach for junction detection and characterization, which especially exploits the locally anisotropic geometries of a junction and estimates its scales by relying on an a-contrario model. The output junctions are with anisotropic scales, saying that a scale parameter is associated with each branch of a junction and are thus named as anisotropic-scale junctions (ASJs). We then apply the new detected ASJs for matching indoor images, where there are dramatic changes of viewpoints and the detected local visual features, e.g., key-points, are usually insufficient and lack distinctive ability. We propose to use the anisotropic geometries of our junctions to improve the matching precision of indoor images. The matching results on sets of indoor images demonstrate that our approach achieves the state-of-the-art performance on indoor image matching.

How to deal with occlusion among persons plays important role in robust multi-pedestrian tracking field. This paper proposes to handle inter-person occlusion by introducing social interaction - attraction and grouping from 2D image plane. This social interaction is systematically studied based on spatial-temporal information without utilizing any scene knowledge. Attraction is integrated into hierarchical data-association as a penalizing factor, while grouping is used to aid target's motion dynamic. The comparison experimental results show that our method achieves results on par with, even better than state-of-the-art online tracking methods.

This paper describes the complete procedure of framework design on a video coding system for error-prone heterogeneous network environment. First of all, system requirements are analyzed and the targets of system design are emphasized on three categories: 1. improve video performance under the constraints of network bandwidth and computational complexity; 2. provide error robust mechanism when packet loss occur; 3. add capability of layered video coding for heterogenous network transmission. Then, ITU-T H.263+ recommendation is introduced, especially about its 16 optional enhanced coding modes: feature, effect and benefit. System design on mode selection is somewhat a trade-off, one hand is improvement on subjective quality of video or other system targets, the other hand is influence on time delay and complexity (computational load, data dependency, ease of implementation, etc.). Five enhanced coding modes are preferred in strong reason for our purpose: Advanced INTRA Coding mode, Deblocking Filter mode, Modified Quantization mode, Slice Structured mode and Temporal, SNR and Spatial Scalability mode. At last, some useful and important system elements beyond H.263+ recommendation are discussed: RTP packetization, error concealment and error tracking. Application shows that all the targets are easily reached by the implementation based on this design.