Feasible Self-Calibration of Larger Field-of-View (FOV) Camera Sensors for the Advanced Driver-Assistance System (ADAS)

• Published in: Sensors (Basel, Switzerland) Vol. 19; no. 15; p. 3369
• Main Authors: Kakani, Vijay, Kim, Hakil, Kumbham, Mahendar, Park, Donghun, Jin, Cheng-Bin, Nguyen, Van Huan
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 31.07.2019; MDPI
• Subjects: advanced driver-assistance system (ADAS); Algorithms; Calibration; International conferences; larger field-of-view (FOV); model-specific empirical γ-residual rectification factor; Optimization techniques; parameter sharing; Pattern recognition; radial distortions; Robotics; self-calibration; Sensors; United States > US; radial distortions; parameter sharing; larger field-of-view (FOV); model-specific empirical γ-residual rectification factor; advanced driver-assistance system (ADAS); self-calibration
• DOI: 10.3390/s19153369
• ISSN: 1424-8220

This paper proposes a self-calibration method that can be applied for multiple larger field-of-view (FOV) camera models on an advanced driver-assistance system (ADAS). Firstly, the proposed method performs a series of pre-processing steps such as edge detection, length thresholding, and edge grouping for the segregation of robust line candidates from the pool of initial distortion line segments. A novel straightness cost constraint with a cross-entropy loss was imposed on the selected line candidates, thereby exploiting that novel loss to optimize the lens-distortion parameters using the Levenberg–Marquardt (LM) optimization approach. The best-fit distortion parameters are used for the undistortion of an image frame, thereby employing various high-end vision-based tasks on the distortion-rectified frame. In this study, an investigation was carried out on experimental approaches such as parameter sharing between multiple camera systems and model-specific empirical γ -residual rectification factor. The quantitative comparisons were carried out between the proposed method and traditional OpenCV method as well as contemporary state-of-the-art self-calibration techniques on KITTI dataset with synthetically generated distortion ranges. Famous image consistency metrics such as peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and position error in salient points estimation were employed for the performance evaluations. Finally, for a better performance validation of the proposed system on a real-time ADAS platform, a pragmatic approach of qualitative analysis has been conducted through streamlining high-end vision-based tasks such as object detection, localization, and mapping, and auto-parking on undistorted frames.