Perceiving accurate 3D object shape is an essential and challenging task for robotic manipulation, which is commonly based on vision systems. However, vision perception suffers from several limitations especially in manipulation tasks where objects are often occluded by the robotic hand. Alternativaly, tactile perception attracts lots of attentions. Due to the low resolution, the density and efficiency of existing tactile-based 3D reconstructions are limited. In order to solve the above problems, this paper describes a vision-based tactile sensor with coded markers. By combining the neighborhood structure coding method and U-net-based decoding algorithm, the sensor can reconstruct high-density 3D object shapes efficiently. Extensive experimental results show the promising sensitivity, accuracy, stability and robustness of our proposed sensor.
Based on tracking-by-detection, we propose a hierarchical-matching-based online and real-time multi-object tracking approach with deep appearance features, which can effectively reduce the false positives (FP) in tracking. For the purpose of increasing the accuracy rate of data association, we define the trajectory confidence using its position information, appearance information, and the information of historical relevant detections, after which we can classify the trajectories into different levels. In order to obtain discriminative appearance features, we developed a deep convolutional neural network to extract the appearance features of objects and trained it on a large-scale pedestrian re-identification dataset. Last but not least, we used the proposed diverse and hierarchical matching strategy to associate detection and trajectory sets. Experimental results on the MOT benchmark dataset show that our proposed approach performs well against other online methods, especially for the metrics of FP and frames per second (FPS).