Monoscopic Automotive Ego-Motion Estimation and Cyclist Tracking
نویسندگان
چکیده
This paper presents concepts, methods and experimental results for estimating the scale of a trajectory that is established by monoscopic Visual Odometry algorithms for use in autonomous driving. While monoscopic Visual Odometry has been widely investigated, one of its key issues restrains its broad appliance: the scale drift. To tackle it, we leverage scene inherent information about the ground plane and external sensors such as a single-row low-cost laser scanner to estimate the scale in real-time. A vision-based calibration method for the registration of a laser scanner and a camera is introduced. The scale corrected trajectory from Visual Odometry is combined with a cyclist tracking to form an Advanced Driver Assistance System, which will be used for collision avoidance between trucks and cyclists.
منابع مشابه
Segmentation Object - Tracking Object - Classification Ego - motion - estimation
Pedestrian protection systems will become an essential safety function in future vehicles as the government will force automotive manufacturer to improve pedestrian safety within the next few years. For such systems the ability to recognise pedestrians is mandatory. This includes detection, tracking and classification of these vulnerable road users. This paper presents a prototype system for pe...
متن کاملEgo-motion Estimation Using Normal Flows
In this paper we propose a novel method to estimate ego-motion parameters of a camera by directly using normal flows. The normal flow field is fully determined by the spatio-temporal derivatives of the image sequence. Therefore, different from traditional methods which achieve the estimation by tracking corresponding features or by calculating the optical flow field, the proposed method could a...
متن کاملLaser Radar based Real-time Ego-motion Estimation for Intelligent Vehicles
Ego-motion estimation is a key issue in intelligent vehicles and important to moving objects tracking. In this paper, after a simple overview of existed method, we present a tangent based hybrid real-time ego-motion estimation algorithm based on laser radar, which is composed of Iterative Tangent weighted Closest Point (ITCP) and Hough transform based Tangent Angle Histogram (HTAH) algorithms t...
متن کاملLaserscanner Innovations for Detection of Obstacles and Road
This paper presents innovations for detection of obstacles and road using a Multilayer Laserscanner. The classification of pedestrians and other road users require robust object tracking algorithms. Their reliability strongly depends on a precise ego-motion compensation. A new method of ego-motion estimation based on relative velocities of tracked objects will be introduced. This method operate...
متن کاملFast Ego-motion Estimation with Multi-rate Fusion of Inertial and Vision
This paper presents a tracking system for ego-motion estimation which fuses vision and inertial measurements using EKF and UKF (Extended and Unscented Kalman Filters), where a comparison of their performance has been done. It also considers the multi-rate nature of the sensors: inertial sensing is sampled at a fast sampling frequency while the sampling frequency of vision is lower. the proposed...
متن کامل