Search

In this paper, we study deep learning approaches for monocular visual odometry (VO). Deep learning solutions have shown to be effective in VO applications, replacing the need for highly engineered steps, such as feature extraction and outlier rejection in a traditional pipeline. We propose a new architecture combining ego-motion estimation and sequence-based learning using deep neural networks. We estimate camera motion from optical flow using Convolutional Neural Networks (CNNs) and model the motion dynamics using Recurrent Neural Networks (RNNs). The network outputs the relative 6-DOF camera poses for a sequence, and implicitly learns the absolute scale without the need for camera intrinsics. The entire trajectory is then integrated without any post-calibration. We evaluate the proposed method on the KITTI dataset and compare it with traditional and other deep learning approaches in the literature.

The required precision for attitude determination in spacecraft is increasing, providing a need for more accurate attitude determination sensors. The star sensor or star tracker provides unmatched arc-second precision and with the rise of micro satellites these sensors are becoming smaller, faster and more efficient. The most critical component in the star sensor system is the lost-in-space star identification algorithm which identifies stars in a scene without a priori attitude information. In this paper, we present an efficient lost-in-space star identification algorithm using a neural network and a robust and novel feature extraction method. Since a neural network implicitly stores the patterns associated with a guide star, a database lookup is eliminated from the matching process. The search time is therefore not influenced by the number of patterns stored in the network, making it constant (O(1)). This search time is unrivalled by other star identification algorithms. The presented algorithm provides excellent performance in a simple and lightweight design, making neural networks the preferred choice for star identification algorithms.

The lost-in-space star identification algorithm is able to identify stars without a priori attitude information and is arguably the most critical component of a star sensor system. In this paper, the 2009 survey by Spratling and Mortari is extended and recent lost-in-space star identification algorithms are surveyed. The covered literature is a qualitative representation of the current research in the field. A taxonomy of these algorithms based on their feature extraction method is defined. Furthermore, we show that in current literature the comparison of these algorithms can produce inconsistent conclusions. In order to mitigate these inconsistencies, this paper lists the considerations related to the relative performance evaluation of these algorithms using simulation.

Embedded systems control and monitor a great deal of our reality. While some "classic" features are intrinsically necessary, such as low power consumption, rugged operating ranges, fast response and low cost, these systems have evolved in the last few years to emphasize connectivity functions, thus contributing to the Internet of Things paradigm. A myriad of sensing/computing devices are being attached to everyday objects, each able to send and receive data and to act as a unique node in the Internet. Apart from the obvious necessity to process at least some data at the edge (to increase security and reduce power consumption and latency), a major breakthrough will arguably come when such devices are endowed with some level of autonomous "intelligence". Intelligent computing aims to solve problems for which no efficient exact algorithm can exist or for which we cannot conceive an exact algorithm. Central to such intelligence is Computer Vision (CV), i.e., extracting meaning from images and video. While not everything needs CV, visual information is the richest source of information about the real world: people, places and things. The possibilities of embedded CV are endless if we consider new applications and technologies, such as deep learning, drones, home robotics, intelligent surveillance, intelligent toys, wearable cameras, etc. This paper describes the Eyes of Things (EoT) platform, a versatile computer vision platform tackling those challenges and opportunities., Competing Interests: The authors declare no conflict of interest.