The invention discloses an all-weather monocular depth estimation algorithm applied to an intelligent driving scene. The all-weather monocular depth estimation algorithm comprises the following steps: (1) constructing an active near-infrared segmented imaging system; (2) performing model construction according to the constructed system, and selecting the model to form a working mode; and (3) loading a working mode. An active near-infrared gating technology is utilized to carry out segmented imaging on different distances of a front sensing area, and depth information of each pixel position of a sensing image of each distance segment is calculated by utilizing a convolutional neural network feature coding and decoding structure; the purposes of improving the anti-interference capability of the camera system under extreme working conditions and providing a stable and reliable depth perception result for intelligent driving are achieved.
本发明公开了一种应用于智能驾驶场景的全天候单目深度估计算法,包含有如下步骤:(1)、进行主动近红外分段成像系统搭建;(2)、根据搭建的系统进行模型构建,对模型进行选择形成工作模式;(3)、加载工作模式。通过利用主动近红外门控技术对前方感知区域的不同距离分段成像,对每个距离段的感知图像利用卷积神经网络特征编码与解码结构计算每个像素位置的深度信息,达到提升摄像系统在极端工况下的抗干扰能力和为智能驾驶提供稳定可靠的深度感知结果的目的。
All-weather monocular depth estimation algorithm applied to intelligent driving scene
一种应用于智能驾驶场景的全天候单目深度估计算法
2024-07-23
Patent
Electronic Resource
Chinese
IPC: | G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06V |
Local Scene Depth Estimation Using Rotating Monocular Camera
British Library Conference Proceedings | 2015
|Local Scene Depth Estimation Using Rotating Monocular Camera
SAE Technical Papers | 2015
|Local scene depth estimation using rotating monocular camera
Automotive engineering | 2015
|