A vision-based blind spot warning system for daytime and nighttime driver assistance

• The BSWS is a vision-based BSD system with dynamic camera calibration and image pre-processing methods.
• The BSWS presents two vision-based BSD algorithms for daytime and nighttime conditions.
• The BSWS is implemented on a DSP-based platform using only two cameras for the camera-assisted car.
• The experimental results of the BSWS demonstrated its effectiveness under both daytime and nighttime conditions.

This paper proposes an effective blind spot warning system (BSWS) for daytime and nighttime conditions. The proposed BSWS includes camera models of a dynamic calibration and blind spot detection (BSD) algorithms for the daytime and nighttime. Under daytime conditions, the proposed system presents the Horizontal Edge and Shadow Composite Region (HESCR) method to extract the searching region and to acquire the shadow location of the targeted vehicles. Additionally, to detect vehicles at nighttime road scenes, the proposed system extracts bright objects and recognizes the paired headlights of the targeted vehicles for the BSD. The BSWS is implemented on a DSP-based embedded platform. The results of the BSWS are obtained by conducting practical experiments on our camera-assisted car on a highway in Taiwan under both nighttime and daytime conditions. Experimental results show that the proposed BSWS is feasible for vehicle detection and collision warning in various daytime and nighttime road environments.

Figure optionsDownload as PowerPoint slide