METHODS, DEVICES, MEDIUM, AND EQUIPMENT FOR DETECTING THREE-DIMENSIONAL OBJECTS AND CONTROLLING INTELLIGENT DRIVING

• Main Authors: KANEDA YUJI, GOTO YUHI, KAWAMURA ATSUSHI, ZENG XINGYU, ARIYOSHI TOKITOMO, WANG XIAOGANG, YAN JUNJIE, LIU SHINAN, YASUI YUJI, CAI YINGJIE
• Format: Patent
• Language: English; Japanese
• Published: 22.10.2020
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS; SIGNALLING; TRAFFIC CONTROL SYSTEMS

To improve 3D object detection accuracy when consumption of computing resources is low, and thus ensure low implementation cost.SOLUTION: A 3D object detection method is provided, comprising: obtaining two-dimensional coordinates of at least one predetermined key point of a target object in an image to be processed (S100); constructing a pseudo 3D detection body of the target object in a 2D space according to the 2D coordinates of the at least one predetermined key point (S110); obtaining depth information of a plurality of vertices of the pseudo 3D detection body (S120); and determining a 3D detection body of the target object in a 3D space according to the depth information of the plurality of vertices of the pseudo 3D detection body (S130).SELECTED DRAWING: Figure 1 【課題】コンピューティングリソースの消費が小さい場合に、対象の三次元検出の精度を向上させ、それにより、低実現コストを確保する。【解決手段】三次元検出方法は、被処理画像内の目標対象の少なくとも１つの所定のキーポイントの二次元座標を取得しＳ１００、所定のキーポイントの二次元座標に従って、前記二次元空間における目標対象の擬似三次元検出体を構築しＳ１１０、擬似三次元検出体の複数の頂点の深度情報を取得しＳ１２０、擬似三次元検出体の複数の頂点の深度情報に従って、三次元空間における目標対象の三次元検出体を決定するＳ１３０。【選択図】図１