Surround-view system (SVS) is widely used in the Advanced Driver Assistance
System (ADAS). SVS uses four fisheye lenses to monitor real-time scenes around
the vehicle. However, accurate intrinsic and extrinsic parameter estimation is
required for the proper functioning of the system. At present, the intrinsic
calibration can be pipeline by utilizing checkerboard algorithm, while
extrinsic calibration is still immature. Therefore, we proposed a specific
calibration pipeline to estimate extrinsic parameters robustly. This scheme
takes a driving sequence of four cameras as input. It firstly utilizes lane
line to roughly estimate each camera pose. Considering the environmental
condition differences in each camera, we separately select strategies from two
methods to accurately estimate the extrinsic parameters. To achieve accurate
estimates for both front and rear camera, we proposed a method that mutually
iterating line detection and pose estimation. As for bilateral camera, we
iteratively adjust the camera pose and position by minimizing texture and edge
error between ground projections of adjacent cameras. After estimating the
extrinsic parameters, the surround-view image can be synthesized by
homography-based transformation. The proposed pipeline can robustly estimate
the four SVS camera extrinsic parameters in real driving environments. In
addition, to evaluate the proposed scheme, we build a surround-view fisheye
dataset, which contains 40 videos with 32,000 frames, acquired from different
real traffic scenarios. All the frames in each video are manually labeled with
lane annotation, with its GT extrinsic parameters. Moreover, this surround-view
dataset could be used by other researchers to evaluate their performance. The
dataset will be available soon.

提出了一种针对车载环视系统（SVS）的校准流程，通过使用巡线检测和姿态估计相互迭代的方法，能够在真实行驶环境中稳健地估计出四个 SVS 相机的外部参数，并构建了包含 40 个视频的车载环视鱼眼数据集，可供其他研究人员用于评估性能。

全景视图系统摄像机校准：基准和数据集

Camera calibration for the surround-view system: a benchmark and dataset

Pedestrian detection under valet parking scenarios is fundamental for
autonomous driving. However, the presence of pedestrians can be manifested in a
variety of ways and postures under imperfect ambient conditions, which can
adversely affect detection performance. Furthermore, models trained on
publicdatasets that include pedestrians generally provide suboptimal outcomes
for these valet parking scenarios. In this paper, wepresent the Parking
Pedestrian Dataset (PPD), a large-scale fisheye dataset to support research
dealing with real-world pedestrians, especially with occlusions and diverse
postures. PPD consists of several distinctive types of pedestrians captured
with fisheye cameras. Additionally, we present a pedestrian detection baseline
on PPD dataset, and introduce two data augmentation techniques to improve the
baseline by enhancing the diversity ofthe original dataset. Extensive
experiments validate the effectiveness of our novel data augmentation
approaches over baselinesand the dataset's exceptional generalizability.

通过 Parking Pedestrian Dataset（PPD）提供的大规模鱼眼数据集，本文介绍了针对真实世界行人，特别是有遮挡和多样的姿势进行研究的行人检测基线，并引入了两种数据增强技术，通过增强原始数据集的多样性来改进基线模型，广泛的实验证实了我们新颖的数据增强方法对基线和数据集的卓越泛化能力。