単眼俯瞰ビューによる自動運転ネットワーク
Monocular Plan View Networks for Autonomous Driving
単眼カメラ映像から検出した車や歩行者を真上から見た俯瞰図に変換し、深層ネットワークで自動運転制御を行う手法を提案。GTA Vシミュレータで衝突回数を大幅に削減した。
著者: Dequan Wang, Coline Devin, Qi-Zhi Cai, Philipp Krähenbühl, Trevor Darrell
分類: cs.CV, cs.RO
原文アブストラクト
Convolutions on monocular dash cam videos capture spatial invariances in the image plane but do not explicitly reason about distances and depth. We propose a simple transformation of observations into a bird's eye view, also known as plan view, for end-to-end control. We detect vehicles and pedestrians in the first person view and project them into an overhead plan view. This representation provides an abstraction of the environment from which a deep network can easily deduce the positions and directions of entities. Additionally, the plan view enables us to leverage advances in 3D object detection in conjunction with deep policy learning. We evaluate our monocular plan view network on the photo-realistic Grand Theft Auto V simulator. A network using both a plan view and front view causes less than half as many collisions as previous detection-based methods and an order of magnitude fewer collisions than pure pixel-based policies.
