Minimum spanning tree (MST) has been devised for non-local cost aggregation to solve the stereo matching problem. However, the cost aggregation is employed directly from leaf toward root node, then in an inverse pass without considering any decision rules. And a small amount of noise is also existed in stereo image pairs. Both of the limitations often lead to failure in achieving more competitive results. This paper presents a novel stereo matching algorithm using forward-backward diffusion and pruning-based cost aggregation. In “forward-backward” process, the raw image pairs are smoothened on a horizontal tree structure as well as retaining image edges sharp. During cost aggregation, the MST where a complete graph involves the whole image pixels is cut off self-adaptively when the depth edge information is referred to. Each node in this tree receives supports from all other nodes which belong to similar depth regions. Meanwhile, an enhanced edge similarity function between two nearest neighboring nodes is formulated to deal with the small-weight-accumulation problem in textureless regions. Consequently, the cost volume can be well aggregated. The proposed method is demonstrated on Middlebury v.2 & v.3 datasets and can obtain good performance in disparity accuracy compared with other five MST based stereo matching methods.

No abstract

When two or more radars with separated space positions and overlapping coverage are used to detect the targets, a radar network is formed. Radar networking can complete data information sharing, improve the reliability of early warning, identification, positioning and detection functions, and improve system functions. Due to the differences in frequency band, platform, system and polarization form of each radar, the deployment process is highly comprehensive. In this paper, a calculation model based on radar detection probability is established for optimal deployment of netted radar. The model takes into account the number of pulse accumulation of pulse radar. The PSO algorithm with variable weight is used to quickly calculate the optimal solution. The best deployment scheme maximizes the detection probability of the netted radar. The simulation results show that the model can describe the detection probability of the netted radar against targets at different distances, and it has important reference value for the optimal deployment of the actual radar network.