The path planning technology is an important part of navigation, which is the core of robotics research. Reinforcement learning is a fashionable algorithm that learns from experience by mimicking the process of human learning skills. When learning new skills, the comprehensive and diverse experience help to refine the grasp of new skills which are called as the depth and the breadth of experience. According to the path planning, this paper proposes an improved learning policy based on the different demand of the experience’s depth and breadth in different learning stages, where the deep Q-networks calculated Q-value adopts the dense network framework. In the initial stage of learning, an experience value evaluation network is created to increase the proportion of deep experience to understand the environmental rules more quickly. When the path wandering phenomenon happens, the exploration of wandering point and other points are taken into account to improve the breadth of the experience pool by using parallel exploration structure. In addition, the network structure is improved by referring to the dense connection method, so the learning and expressive abilities of the network are improved to some extent. Finally, the experimental results show that our model has certain improvement in convergence speed, planning success rate and path accuracy. Under the same experimental conditions, the method of this paper is compared with the conventional intensive learning method via deep Q-networks. The results show that the indicators of this method are significantly higher.

Segmentation of left and right ventricles from 3D echocardiographic images is premised and key for quantitative analysis of cardiac function, which is important for pediatric cardiac diagnosis. Compared with 2D echocardiography, 3D echocardiography can fully represent ventricular structure without geometric inference. However, it usually takes experts several hours to obtain a 3D segmentation mask of the left and right ventricles. Therefore, a fast and automatic segmentation method is highly desired. Unfortunately, 3D echocardiography suffers from low contrast, unclear left and right ventricles borders, and blind zone. Existing segmentation methods usually have poor performance at ventricular boundaries. To deal with these problems, we propose a novel dual-branch TransV-Net (DBTV). DBTV comprises two parallel, interleaved, and relatively independent V-shaped encoder-decoder branches. The main branch acts on the original data to extract image features, and the auxiliary branch acts on edge maps to extract the additional edge features. To suppress noise and enhance the edge information, extra concatenations are added to bridge the features from the main and auxiliary branches. To reduce object missing caused by blind zone, a 3D transformer-based module is proposed in the bottom layer of the dual-branch structure to extract the global contexts. We do experiments on a self-collected dataset with 120 3D echocardiographic images from 60 cardiac sequences, and the dice score of 0.913 and 0.880 are obtained in the left and right ventricle segments, respectively. Each inference takes about two-thirds of a second for a single 3D frame.

For the existing image matching algorithms, some inherent shortcomings, such as high mismatch rate and low computational efficiency, give rise to a bad influence on the performance of Visual Simultaneous Localization and Mapping (VSLAM). In this paper, a Grid-Based Motion Statistics for Fast and Random Sample Consensus (GMS-RANSAC) method combining with Multi-Probe Location Sensitive Hash (LSH)-based Adaptive and Generic Corner Detection Based on the Accelerated Segment Test and Oriented FAST and Rotated BRIEF (AGAST-ORB) algorithm is proposed to improve the real time and accuracy of image matching. To this end, the AGAST algorithm and the multi-probe LSH algorithm are firstly integrated into the traditional ORB algorithm to obtain the initial matching set. Specifically, the image feature points are extracted by the AGAST algorithm and then the main direction of feature points is given according to the intensity centroid method to guarantee the rotary invariant of feature points. Based on the extracted feature points, the multi-probe LSH algorithm, benefiting from its high time efficiency, is used to generate the initial matching pairs. In what follows, a GMS-RANSAC algorithm, which is improved by adding a directional similarity constraint model and the traditional RANSAC algorithm, is performed to improve the accuracy of eliminating result further. Finally, the performance test is implemented via a Mikolajczyk standard data set and it is verified that the proposed algorithm has higher matching precision and matching efficiency than traditional image matching algorithms.