No abstract

No abstract

3D object recognition is an generic task in robotics and autonomous vehicles. In this paper, we propose a 3D object recognition approach using a 3D extension of the histogram-of-gradients object descriptor with data captured with a depth camera. The presented method makes use of synthetic objects for training the object classifier, and classify real objects captured by the depth camera. The preprocessing methods include operations to achieve rotational invariance as well as to maximize the recognition accuracy while reducing the feature dimensionality at the same time. By studying different preprocessing options, we show challenges that need to be addressed when moving from synthetic to real data. The recognition performance was evaluated with a real dataset captured by a depth camera and the results show a maximum recognition accuracy of 81.5%.

Fiber-fed spectrographs dedicated to observing massive portions of the sky are increasingly being more demanded within the astronomical community. For all the fiber-fed instruments, the primordial and common problem is the positioning of the fiber ends, which must match the position of the objects of a target field on the sky. Amongst the different approaches found in the state of the art, actuator arrays are one of the best. Indeed, an actuator array is able to position all the fiber heads simultaneously, thus making the reconfiguration time extremely short and the instrument efficiency high. The SIDE group * at the Instituto de Astrofísica de Andalucía, together with the industrial company AVS and the University of Barcelona, has been developing an actuator suitable for a large and scalable array. A real-scale prototype has been built and tested in order to validate its innovative design concept, as well as to verify the fulfillment of the mechanical requirements. The present article describes both the concept design and the test procedures and conditions. The main results are shown and a full justification of the validity of the proposed concept is provided.

3D object recognition has been a cutting-edge research topic since the popularization of depth cameras. These cameras enhance the perception of the environment and so are particularly suitable for autonomous robot navigation applications. Advanced deep learning approaches for 3D object recognition are based on complex algorithms and demand powerful hardware resources. However, autonomous robots and powered wheelchairs have limited resources, which affects the implementation of these algorithms for real-time performance. We propose to use instead a 3D voxel-based extension of the 2D histogram of oriented gradients (3DVHOG) as a handcrafted object descriptor for 3D object recognition in combination with a pose normalization method for rotational invariance and a supervised object classifier. The experimental goal is to reduce the overall complexity and the system hardware requirements, and thus enable a feasible real-time hardware implementation. This article compares the 3DVHOG object recognition rates with those of other 3D recognition approaches, using the ModelNet10 object data set as a reference. We analyze the recognition accuracy for 3DVHOG using a variety of voxel grid selections, different numbers of neurons ( Nh) in the single hidden layer feedforward neural network, and feature dimensionality reduction using principal component analysis. The experimental results show that the 3DVHOG descriptor achieves a recognition accuracy of 84.91% with a total processing time of 21.4 ms. Despite the lower recognition accuracy, this is close to the current state-of-the-art approaches for deep learning while enabling real-time performance.