《電子技術(shù)應(yīng)用》
您所在的位置:首頁 > 人工智能 > 设计应用 > 基于点云补全的三维目标检测
基于点云补全的三维目标检测
2023年电子技术应用第8期
陈辉,王帅杰,蔡晗
(桂林电子科技大学 信息与通信学院, 广西 桂林 541004)
摘要: LiDAR技术的发展为自动驾驶提供了丰富的3D数据。然而,由于遮挡和某些反射材料的原因引起信号丢失,LiDAR点云实际上是不完整的2.5D数据,这对 3D 感知提出了根本性挑战。针对这一问题,提出对原始数据进行三维补全的方法。根据大多数物体形状对称且重复率高的特点,通过学习先验对象形状的方法估计点云中遮挡部分的完整形状。该方法首先识别被遮挡和信号缺失影响的区域,在这些区域中预测区域所包含对象形状的占用概率。针对物体间遮挡的情况,通过形状的占用概率和共享同类形状形态进行三维补全。对自身遮挡的物体,通过自身镜像进行恢复。最后通过点云目标检测网络进行学习。结果表明,通过该方法能有效地提高生成点云3D边框的mAP(mean Average Precision)。
關(guān)鍵詞: LIDAR 点云 三维补全 目标检测
中圖分類號:TP389.1
文獻標(biāo)志碼:A
DOI: 10.16157/j.issn.0258-7998.223624
中文引用格式: 陳輝,王帥杰,蔡晗. 基于點云補全的三維目標(biāo)檢測[J]. 電子技術(shù)應(yīng)用,2023,49(8):1-6.
英文引用格式: Chen Hui,Wang Shuaijie,Cai Han. 3D object detection based on point cloud completion[J]. Application of Electronic Technique,2023,49(8):1-6.
3D object detection based on point cloud completion
Chen Hui,Wang Shuaijie,Cai Han
(School of lnformation and Communication, Guilin University of Electronic Technology, Guilin 541004, China)
Abstract: The development of LiDAR technology provides abundant 3D data for autonomous driving. However, LIDAR point cloud is actually incomplete 2.5D data due to signal loss caused by occlusion and some reflective materials, which poses a fundamental challenge to 3D perception. To solve this problem, this paper proposes a method for 3D completion of the original data. According to the symmetric shape and high repetition rate of most objects, the complete shape of the occluded part in the point cloud is estimated by learning the prior object shape. The method first identifies regions affected by occlusions and signal loss, and in these regions, predicts the occupancy probability of the shapes of objects contained in the regions. For the case of occlusion between objects, 3D completion is performed through the occupancy probability of the shape and the morphologies that share the same shape. The objects occluded by themselves are restored by mirroring themselves. Finally, it is learned through the point cloud target detection network. The results show that this method can effectively improve the mAP for generating point cloud 3D borders.
Key words : LiDAR;point cloud;3D completion;target detection

0 引言

3D目標(biāo)檢測作為自動駕駛感知系統(tǒng)的核心基礎(chǔ)之一,可以廣泛應(yīng)用于路徑規(guī)劃、運動預(yù)測、碰撞避免等功能。通常,帶有相應(yīng)3D激光雷傳感器的汽車已經(jīng)成自動駕駛領(lǐng)域的標(biāo)準(zhǔn)配置,由此能夠提供準(zhǔn)確的深度信息,點云數(shù)據(jù)的處理也越來越普遍、越來越重要。盡管已有很多進展,但由于點云本質(zhì)上的高度稀疏性和不規(guī)則的特性,使得傳統(tǒng)的卷積神經(jīng)網(wǎng)絡(luò)無法對點云數(shù)據(jù)進行準(zhǔn)確的學(xué)習(xí),而且由于相機視圖和激光雷達(dá)鳥瞰視圖之間的不對齊而導(dǎo)致的導(dǎo)致模態(tài)協(xié)同和遠(yuǎn)距離尺度變化等原因,三維點云的處理遠(yuǎn)比二維圖像要難得多。因此,在三維點云上的目標(biāo)檢測目前仍處于初級階段。



本文詳細(xì)內(nèi)容請下載:http://m.ihrv.cn/resource/share/2000005474




作者信息:

陳輝,王帥杰,蔡晗

(桂林電子科技大學(xué) 信息與通信學(xué)院, 廣西 桂林 541004)

微信圖片_20210517164139.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。