Most sensor setups for onboard autonomous perception are composed of LiDARs and vision systems, as they provide complementary information that improves the reliability of the different algorithms necessary to obtain a robust scene understanding. However, the effective use of information from different sources requires an accurate calibration between the sensors involved, which usually implies a tedious and burdensome process. We present a method to calibrate the extrinsic parameters of any pair of sensors involving LiDARs, monocular or stereo cameras, of the same or different modalities. The procedure is composed of two stages: first, reference points belonging to a custom calibration target are extracted from the data provided by the sensors to be calibrated, and second, the optimal rigid transformation is found through the registration of both point sets. The proposed approach can handle devices with very different resolutions and poses, as usually found in vehicle setups. In order to assess the performance of the proposed method, a novel evaluation suite built on top of a popular simulation framework is introduced. Experiments on the synthetic environment show that our calibration algorithm significantly outperforms existing methods, whereas real data tests corroborate the results obtained in the evaluation suite. Open-source code is available at https://github.com/beltransen/velo2cam_calibration .

The advances in Information Technologies have led to more complex road safety applications. These systems provide multiple possibilities for improving road transport. The integrated system that this paper presents deals with two aspects that have been identified as key topics: safety and efficiency. To this end, the development and implementation of an integrated advanced driver assistance system (ADAS) for rural and intercity environments is proposed. The system focuses mainly on single-carriageways roads, given the complexity of these environments compared to motorways and the high number of severe and fatal accidents on them. The proposed system is based on advanced perception techniques, vehicle automation and communications between vehicles (V2V) and with the infrastructure (V2I). Sensor fusion architecture based on computer vision and laser scanner technologies are developed. It allows real time detection and classification of obstacles, and the identification of potential risks. The driver receives this information and some warnings generated by the system. In case, he does not react in a proper way, the vehicle could perform autonomous actions (both on speed control or steering maneuvers) to improve safety and/or efficiency. Furthermore, a multimodal V2V and V2I communication system, based on GeoNetworking, facilitates the flow of information between vehicles and assists in the detection and information broadcasting processes. All this, combined with vehicle positioning, detailed digital maps and advanced map-matching algorithms, establish the decision algorithms of different ADAS systems.The applications developed include: adaptive cruise control with consumption optimization, overtaking assistance system in single-carriageways roads that takes into account appropriate speed evolution and identifies most suitable road stretches for the maneuver; assistance system in intersections with speed control during approximation maneuvers, and collision avoidance system with the possibility of evasive maneuvers. To this end, mathematical vehicle dynamics models have been used to ensure the stability, and propulsion system models are used to establish efficient patterns, Artificial Intelligence and simulation are used for experimentation and evaluation of algorithms to be implemented in the control unit. Finally, the system is designed to warn the driver if a risk is detected and, if necessary, to take control of the vehicle. The system has been implemented on a passenger car and has been tested in specific scenarios on a test track with satisfactory results

One of the most challenging problems in the domain of autonomous aerial vehicles is the designing of a robust real-time obstacle detection and avoidance system. This problem is complex, especially for the micro and small aerial vehicles, that is due to the Size, Weight and Power (SWaP) constraints. Therefore, using lightweight sensors (i.e., Digital camera) can be the best choice comparing with other sensors; such as laser or radar.For real-time applications, different works are based on stereo cameras in order to obtain a 3D model of the obstacles, or to estimate their depth. Instead, in this paper, a method that mimics the human behavior of detecting the collision state of the approaching obstacles using monocular camera is proposed. The key of the proposed algorithm is to analyze the size changes of the detected feature points, combined with the expansion ratios of the convex hull constructed around the detected feature points from consecutive frames. During the Aerial Vehicle (UAV) motion, the detection algorithm estimates the changes in the size of the area of the approaching obstacles. First, the method detects the feature points of the obstacles, then extracts the obstacles that have the probability of getting close toward the UAV. Secondly, by comparing the area ratio of the obstacle and the position of the UAV, the method decides if the detected obstacle may cause a collision. Finally, by estimating the obstacle 2D position in the image and combining with the tracked waypoints, the UAV performs the avoidance maneuver. The proposed algorithm was evaluated by performing real indoor and outdoor flights, and the obtained results show the accuracy of the proposed algorithm compared with other related works.

A novel sensor fusion methodology is presented, which provides intelligent vehicles with augmented environment information and knowledge, enabled by vision-based system, laser sensor and global positioning system. The presented approach achieves safer roads by data fusion techniques, especially in single-lane carriage-ways where casualties are higher than in other road classes, and focuses on the interplay between vehicle drivers and intelligent vehicles. The system is based on the reliability of laser scanner for obstacle detection, the use of camera based identification techniques and advanced tracking and data association algorithms i.e. Unscented Kalman Filter and Joint Probabilistic Data Association. The achieved results foster the implementation of the sensor fusion methodology in forthcoming Intelligent Transportation Systems.

The use of smartphones in a road context by drivers and Vulnerable Road Users (VRU) is rapidly increasing. To reduce the risks related to the influence of smartphone usage in a situation where traffic needs to be considered, a collision prediction algorithm is proposed based on Pedestrian to Vehicle (P2V) and Vehicle to Pedestrian (V2P) communication technologies, which increases the visual situational awareness of VRU regarding the nearby location of both autonomous and manually-controlled vehicles in a user-friendly form. The proposed application broadcasts the device's position to the vehicles nearby, and reciprocally, the vehicles nearby broadcast their position to the device in use, supporting pedestrians and other VRU to minimize potential dangers and increase the acceptance of autonomous vehicles on our roads. Results regarding the evaluation of the proposed approach showed a good performance and high detection rate, as well as a high user satisfaction derived from the interaction with the system.