Domain generalization aims to apply knowledge gained from multiple labeled source domains to unseen target domains. The main difficulty comes from the dataset bias: Training data and test data have different distribut...
详细信息
Recently, numerous salient object detection methods are proposed for different data types. And a reliable method, which can accurately extract complete salient objects, is beneficial to various vision tasks. However, ...
详细信息
ISBN:
(纸本)9781509060689
Recently, numerous salient object detection methods are proposed for different data types. And a reliable method, which can accurately extract complete salient objects, is beneficial to various vision tasks. However, existing methods may fail in highlighting the entire salient object uniformly. In this work, we propose a simple and universal framework aiming to improve the detection result of existing methods. To remove inaccurate salient regions, we apply location prior and adaptive de-noising to prior saliency maps extracted from existing methods in the pre-processing step. Then, an iteration optimization algorithm considering local smoothness and global similarity is introduced to refine the pre-processed saliency map. The experimental results show that the proposed framework can universally enhance the performance of state-of-the-art salient object detection methods for 2D, 3D and light field data.
Vehicle re-identification (re-id) plays an important role in the automatic analysis of the drastically increasing urban surveillance videos. Similar to the other image retrieval problems, vehicle re-id suffers from th...
详细信息
ISBN:
(纸本)9781509060689
Vehicle re-identification (re-id) plays an important role in the automatic analysis of the drastically increasing urban surveillance videos. Similar to the other image retrieval problems, vehicle re-id suffers from the difficulties caused by various poses of vehicles, diversified illuminations, and complicated environments. Triplet-wise training of convolutional neural network (CNN) has been studied to address these challenges, where the CNN is adopted to automate the feature extraction from images, and the training adopts triplets of (query, positive example, negative example) to capture the relative similarity between them to learn representative features. The traditional triplet-wise training is weakly constrained and thus fails to achieve satisfactory results. We propose to improve the triplet-wise training at two aspects: first, a stronger constraint namely classification-oriented loss is augmented with the original triplet loss; second, a new triplet sampling method based on pairwise images is designed. Our experimental results demonstrate the effectiveness of the proposed methods that achieve superior performance than the state-of-the-arts on two vehicle re-id datasets, which are derived from real-world urban surveillance videos.
This paper is concerned with developing a novel distributed Kalman filtering algorithm over wireless sensor networks based on randomized consensus strategy. Compared with centralized algorithm, distributed filtering t...
详细信息
In both H.264 and HEVC, context-adaptive binary arithmetic coding (CABAC) is adopted as the entropy coding method. CABAC relies on manually designed binarization processes as well as handcrafted context models, which ...
详细信息
Motion compensation is a fundamental technology in video coding to remove the temporal redundancy between video frames. To further improve the coding efficiency, sub-pel motion compensation has been utilized, which re...
详细信息
Segmentation of point clouds has been studied under a variety of scenarios. However, the segmentation of scanned point clouds for a clustered indoor scene remains significantly challenging due to noisy and incomplete ...
详细信息
ISBN:
(纸本)9781509063451
Segmentation of point clouds has been studied under a variety of scenarios. However, the segmentation of scanned point clouds for a clustered indoor scene remains significantly challenging due to noisy and incomplete data, as well as scene complexity. Based on the observation that objects in an indoor scene vary largely in scale but are typically supported by planes, we propose a co-segmentation approach. This technique utilizes the mutual agency between the point clouds captured at different times after the objects' poses change due to human actions. Hence, we hierarchically segment scenes from different times into patches and generate tree structures to store their relations. By iteratively clustering patches and co-analyzing them based on the relations between patches, we modify the tree structures and generate our results. To test the robustness of our method, we evaluate it on imperfectly scanned point clouds from a childroom, a bedroom, and two offices scenes.
A class of networked control systems is investigated whose communication network is shared with other applications. The design objective for such a system setting is not only the optimization of the control performanc...
详细信息
A class of networked control systems is investigated whose communication network is shared with other applications. The design objective for such a system setting is not only the optimization of the control performance but also the efficient utilization of the communication resources. We observe that at a large time scale the data packet delay in the communication network is roughly varying piecewise constant, which is typically true for data networks like the Internet. Based on this observation, a dynamic data packing scheme is proposed within the recently developed packet-based control framework for networked control systems. As expected this proposed approach achieves a fine balance between the control performance and the communication utilization: the similar control performance can be obtained at dramatically reduced cost of the communication resources. Simulations illustrate the effectiveness of the proposed approach.
Gaofen-3 is the first C-band fully polarimetric SAR satellite in China, which is widely used in various fields such as ocean monitoring, disaster reduction and so on. In this paper, a new satellite constellation is pr...
详细信息
Gaofen-3 is the first C-band fully polarimetric SAR satellite in China, which is widely used in various fields such as ocean monitoring, disaster reduction and so on. In this paper, a new satellite constellation is proposed based on the orbit of Gaofen-3 satellite. The constellation includes Gaofen-3 and other two duplicates. It is able to do repeat-pass interferometry, repeat-pass differential interferometry, along-track interferometry and stereo measurement. With these abilities, it can generate the earth DEM without ground control points and have better performance in moving target identification and monitoring. The performance and the system requirements are analysed, which provides a good reference for the design of spaceborne SAR constellation.
This paper reports the repeat-pass interferometric SAR results of Gaofen-3, a Chinese civil SAR satellite, acquired in November 2016 and March 2017 from Ningbo area. With the spatial baseline about 600 m and time base...
详细信息
暂无评论