A real-time vehicle safety system by concurrent object detection and head pose estimation via stereo vision.

A considerable number of vehicular accidents occur in low-millage zones like school streets, neighborhoods, and parking lots, among others. Therefore, the proposed work aims to provide a novel ADAS system to warn about dangerous scenarios by analyzing the driver's attention and the corresponding distances between the vehicle and the detected object on the road. This approach is made possible by concurrent Head Pose Estimation (HPE) and Object/Pedestrian Detection. Both approaches have shown independently their viable application in the automotive industry to decrease the number of vehicle collisions. The proposed system takes advantage of stereo vision characteristics for HPE by enabling the computation of the Euler Angles with a low average error for classifying the driver's attention on the road using neural networks. For Object Detection, stereo vision is used to detect the distance between the vehicle and the approaching object; this is made with a state-of-the-art algorithm known as YOLO-R and a fast template matching technique known as SoRA that provides lower processing times. The result is an ADAS system designed to ensure adequate braking time, considering the driver's attention on the road and the distances to objects.

Determination of trajectories using IKZ/CF inertial navigation: Methodological proposal.

Nowadays, there are different methods used in the autonomous navigation task; current solutions include inertial navigation systems (INS). However, these systems present drift errors that are attenuated by the integration of absolute reference systems such as GPS, and antennas, among others. Consequently, few works concentrate efforts on developing a methodology to reduce drift errors in INS due to the widespread practice of incorporating absolute references into their systems. However, absolute references must be placed beforehand, which is not always possible. This work presents an improvement on our methodological proposal IKZ for tracking and localization of moving objects by integrating a complementary filter (CF). The main contribution of this paper is the methodological proposal in the integration between IKZ and CF, maintaining the restrictive properties to the drift error and significantly improving the handling characteristics of the system in real applications. Furthermore, the IKZ/CF was tested with raw data from an MPU-9255 in order to analyze the results between tests.