Depth information perception of unstructured scene images is an important problem for applications using computer vision. This paper proposes a method based on deep learning combined with self-attention mechanism to reason the depth information of unstructured indoor targets, which effectively solves the problem of blurred image detail and insufficient layering in depth information reasoning in unstructured scenes. First, the deep learning-based encoder-decoder model is trained to learn the depth information of indoor scenes on large 3D datasets. The trained model has good results for general structured indoor scenes. Secondly, the soft self-attention mechanism is used to obtain the disparity information between the upper and lower sequences of the input image, by which the depth map obtained in the first step is corrected to enhance the accuracy of depth. Finally, in order to get clear objects with obvious boundaries in the depth response map, the nearest neighbor regression is used to correct the contour of the objects. The experimental results show that the proposed method has very good depth information reasoning ability for indoor unstructured scenes. Through depth information reasoning, the obtained objects have obvious texture structure, strong geometric features, clear contour edges and delicate layers, and also the misleading of deep information reasoning in reflective and highlight areas is eliminated.
Due to the excessively dense steel coil layers on the end face of the rolled coil, it is difficult to extract the defect area of the end face of rolled steel by the image segmentation methods such as edge detection and threshold segmentation. Aiming at the dense texture features of the end face of rolled steel coil, a method of detecting the defects of the end face of steel coils was proposed. Based on the theoretical technology of machine vision, this paper proposed a double threshold method to extract potential defect area and eliminate the background area and the completely defect-free area. In the double threshold method, we utilize the Canny operator and the PPHT (Progressive Probabilistic Hough Transform) to adjust the direction of the image block on the end face of the steel coils, makes the texture direction on each image block consistent. Then, Gaussian steerable filter, followed by second Canny and PPHT, was applied to enhance image. After the double threshold method, projective integral of digital image was utilized to extract the feature of the potential defects area. Finally, the SVM (Support Vector Machine) is applied to determine the type of the defect. The results show that the method of detecting the defects of the end face of steel coils can accurately and quickly detect defects even on the end face image of the steel coils with dense layers.
Obstacles detection is one of the most important parts for ADAS (Advanced Driver Assistance Systems). Camera provides excellent recognition but with limits to range information; nevertheless, the LiDAR allows for better range information but with limits to the object identification. This paper deals with the problem of efficiently and accurately detecting vehicles on-load by fusing color images and LiDAR point clouds. Firstly, a neural network is used to detect road and vehicles. This neural network has high accuracy and speed on detection for the encoder in it is shared by different tasks. In the second step, the point clouds are processed to remove some invalid points and positions that potential represent targets generate by clustering point clouds. Positions are projected to images plane to get the ROI (Region of Interest), then the ROI will be matched with detection results of image to check if any targets are missed. In the paper, we adopt the RANSAC (Random Sample Consensus) algorithm to remove ground points. A parameter adaptive DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm is proposed to cluster points, where parameters can change adaptively according to the characteristics of different density point clouds. Through neural network, we recognize the types of obstacles. Experiment is performed on KITTI dataset, using left color images and Velodyne64 point clouds to verify our method. The result shows satisfactory accuracy in detection work.
Robotic blimps present an enormous potential for applications in low-speed and low-altitude exploration, surveillance, and monitoring, as well as telecommunication relay platforms. To make our lighter-than-air platform a robotic blimp with significant levels of autonomy, the decoupled longitude and latitude dynamic model are developed, and the hardware and software of the flight control system are designed. The onboard hardware consists of blimp state observer, actuators, MCU, etc. The software functions include signals processing, data filtering and fault tolerance, ground command execution, etc. Based on decoupled dynamic model, the control system architecture is presented, and navigation strategy for waypoint flight problem is discussed. The paper gives results of a flight experiment using the designed flight control system, and the results manifests that the system is applicable and initial machine intelligence of robotic blimp is achieved.