TELIN-IPI, Ghent University - imec, St-Pietersnieuwstraat 41, B-9000 Gent, Belgium.
Sensors (Basel). 2019 Jan 18;19(2):391. doi: 10.3390/s19020391.
In this paper, we present a novel 2D⁻3D pedestrian tracker designed for applications in autonomous vehicles. The system operates on a tracking by detection principle and can track multiple pedestrians in complex urban traffic situations. By using a behavioral motion model and a non-parametric distribution as state model, we are able to accurately track unpredictable pedestrian motion in the presence of heavy occlusion. Tracking is performed independently, on the image and ground plane, in global, motion compensated coordinates. We employ Camera and LiDAR data fusion to solve the association problem where the optimal solution is found by matching 2D and 3D detections to tracks using a joint log-likelihood observation model. Each 2D⁻3D particle filter then updates their state from associated observations and a behavioral motion model. Each particle moves independently following the pedestrian motion parameters which we learned offline from an annotated training dataset. Temporal stability of the state variables is achieved by modeling each track as a Markov Decision Process with probabilistic state transition properties. A novel track management system then handles high level actions such as track creation, deletion and interaction. Using a probabilistic track score the track manager can cull false and ambiguous detections while updating tracks with detections from actual pedestrians. Our system is implemented on a GPU and exploits the massively parallelizable nature of particle filters. Due to the Markovian nature of our track representation, the system achieves real-time performance operating with a minimal memory footprint. Exhaustive and independent evaluation of our tracker was performed by the KITTI benchmark server, where it was tested against a wide variety of unknown pedestrian tracking situations. On this realistic benchmark, we outperform all published pedestrian trackers in a multitude of tracking metrics.
在本文中，我们提出了一种新颖的 2D-3D 行人跟踪器，专为自动驾驶汽车中的应用而设计。该系统采用基于检测的跟踪原理，可以在复杂的城市交通环境中跟踪多个行人。通过使用行为运动模型和非参数分布作为状态模型，我们能够在存在严重遮挡的情况下准确跟踪不可预测的行人运动。跟踪在全局、运动补偿坐标上的图像和地面平面上独立进行。我们采用相机和激光雷达数据融合来解决关联问题，通过使用联合对数似然观测模型将 2D 和 3D 检测与跟踪进行匹配，找到最佳解决方案。每个 2D-3D 粒子滤波器然后从关联观测和行为运动模型更新其状态。每个粒子根据我们从带注释的训练数据集中学到的行人运动参数独立移动。通过将每个跟踪建模为具有概率状态转移特性的马尔可夫决策过程来实现状态变量的时间稳定性。然后，一个新的跟踪管理系统处理诸如创建、删除和交互等高级操作。使用概率跟踪得分，跟踪管理器可以在更新来自实际行人的检测时剔除虚假和模糊的检测。我们的系统在 GPU 上实现，并利用粒子滤波器的大规模并行性。由于我们的跟踪表示具有马尔可夫性质，因此系统以最小的内存占用实现了实时性能。通过 KITTI 基准服务器对我们的跟踪器进行了全面且独立的评估，在各种未知行人跟踪情况下对其进行了测试。在这个现实的基准测试中，我们在多种跟踪指标上优于所有已发布的行人跟踪器。
