Xiaofei Zhang, Zhengping Fan, Ying Shen, Yining Li, Yasong An, Xiaojun Tan
{"title":"MAEMOT:用于自动驾驶的基于 MAE 的预训练反排斥三维多目标跟踪。","authors":"Xiaofei Zhang, Zhengping Fan, Ying Shen, Yining Li, Yasong An, Xiaojun Tan","doi":"10.1109/TNNLS.2024.3480148","DOIUrl":null,"url":null,"abstract":"<p><p>The existing 3-D multiobject tracking (MOT) methods suffer from object occlusion in real-world traffic scenes. However, previous works have faced challenges in providing a reasonable solution to the fundamental question: \"How can the interference of the perception data loss caused by occlusion be overcome?\" Therefore, this article attempts to provide a reasonable solution by developing a novel pretrained movement-constrained masked autoencoder (M-MAE) for an antiocclusion 3-D MOT called MAEMOT. Specifically, for the pretrained M-MAE, this article adopts an efficient multistage transformer (MST) encoder and a spatiotemporal-based motion decoder to predict and reconstruct occluded point cloud data, following the properties of object motion. Afterward, the well-trained M-MAE model extracts the global features of occluded objects, ensuring that the features of the intraobjects between interframes are as consistent as possible throughout the spatiotemporal sequence. Next, a proposal-based geometric graph aggregation (PG <sup>2</sup> A) module is utilized to extract and fuse the spatial features of each proposal, producing refined region-of-interest (RoI) components. Finally, this article designs an object association module that combines geometric and corner affinities, which helps to match the predicted occlusion objects more robustly. According to an extensive evaluation, the proposed MAEMOT method can effectively overcome the interference of occlusion and achieve improved 3-D MOT performance under challenging conditions.</p>","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2000,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"MAEMOT: Pretrained MAE-Based Antiocclusion 3-D Multiobject Tracking for Autonomous Driving.\",\"authors\":\"Xiaofei Zhang, Zhengping Fan, Ying Shen, Yining Li, Yasong An, Xiaojun Tan\",\"doi\":\"10.1109/TNNLS.2024.3480148\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>The existing 3-D multiobject tracking (MOT) methods suffer from object occlusion in real-world traffic scenes. However, previous works have faced challenges in providing a reasonable solution to the fundamental question: \\\"How can the interference of the perception data loss caused by occlusion be overcome?\\\" Therefore, this article attempts to provide a reasonable solution by developing a novel pretrained movement-constrained masked autoencoder (M-MAE) for an antiocclusion 3-D MOT called MAEMOT. Specifically, for the pretrained M-MAE, this article adopts an efficient multistage transformer (MST) encoder and a spatiotemporal-based motion decoder to predict and reconstruct occluded point cloud data, following the properties of object motion. Afterward, the well-trained M-MAE model extracts the global features of occluded objects, ensuring that the features of the intraobjects between interframes are as consistent as possible throughout the spatiotemporal sequence. Next, a proposal-based geometric graph aggregation (PG <sup>2</sup> A) module is utilized to extract and fuse the spatial features of each proposal, producing refined region-of-interest (RoI) components. Finally, this article designs an object association module that combines geometric and corner affinities, which helps to match the predicted occlusion objects more robustly. According to an extensive evaluation, the proposed MAEMOT method can effectively overcome the interference of occlusion and achieve improved 3-D MOT performance under challenging conditions.</p>\",\"PeriodicalId\":13303,\"journal\":{\"name\":\"IEEE transactions on neural networks and learning systems\",\"volume\":\"PP \",\"pages\":\"\"},\"PeriodicalIF\":10.2000,\"publicationDate\":\"2024-10-31\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on neural networks and learning systems\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1109/TNNLS.2024.3480148\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on neural networks and learning systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1109/TNNLS.2024.3480148","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
摘要
现有的三维多目标跟踪(MOT)方法在现实世界的交通场景中受到目标遮挡的困扰。然而,以往的研究在为这一根本问题提供合理解决方案方面面临挑战:"如何克服遮挡对感知数据丢失的干扰?因此,本文试图通过为一种名为 MAEMOT 的抗遮挡三维 MOT 开发一种新型预训练运动约束遮挡自动编码器(M-MAE)来提供一种合理的解决方案。具体来说,对于预训练的 M-MAE,本文采用了高效的多级变换器(MST)编码器和基于时空的运动解码器,根据物体运动的特性来预测和重建遮挡点云数据。之后,训练有素的 M-MAE 模型会提取被遮挡物体的全局特征,确保帧间物体内部特征在整个时空序列中尽可能保持一致。然后,利用基于提案的几何图聚合(PG 2 A)模块提取并融合每个提案的空间特征,生成细化的兴趣区域(RoI)组件。最后,本文设计了一个对象关联模块,该模块结合了几何亲和力和角落亲和力,有助于更稳健地匹配预测的闭塞对象。通过广泛的评估,所提出的 MAEMOT 方法可以有效克服遮挡干扰,在具有挑战性的条件下提高三维 MOT 性能。
MAEMOT: Pretrained MAE-Based Antiocclusion 3-D Multiobject Tracking for Autonomous Driving.
The existing 3-D multiobject tracking (MOT) methods suffer from object occlusion in real-world traffic scenes. However, previous works have faced challenges in providing a reasonable solution to the fundamental question: "How can the interference of the perception data loss caused by occlusion be overcome?" Therefore, this article attempts to provide a reasonable solution by developing a novel pretrained movement-constrained masked autoencoder (M-MAE) for an antiocclusion 3-D MOT called MAEMOT. Specifically, for the pretrained M-MAE, this article adopts an efficient multistage transformer (MST) encoder and a spatiotemporal-based motion decoder to predict and reconstruct occluded point cloud data, following the properties of object motion. Afterward, the well-trained M-MAE model extracts the global features of occluded objects, ensuring that the features of the intraobjects between interframes are as consistent as possible throughout the spatiotemporal sequence. Next, a proposal-based geometric graph aggregation (PG 2 A) module is utilized to extract and fuse the spatial features of each proposal, producing refined region-of-interest (RoI) components. Finally, this article designs an object association module that combines geometric and corner affinities, which helps to match the predicted occlusion objects more robustly. According to an extensive evaluation, the proposed MAEMOT method can effectively overcome the interference of occlusion and achieve improved 3-D MOT performance under challenging conditions.
期刊介绍:
The focus of IEEE Transactions on Neural Networks and Learning Systems is to present scholarly articles discussing the theory, design, and applications of neural networks as well as other learning systems. The journal primarily highlights technical and scientific research in this domain.