SPARK: Low Latency Single-Camera 3D Pose Estimation for Autonomous Racing using Keypoints

• URL: http://arxiv.org/abs/2606.17936v2
• Date: Thu, 25 Jun 2026 09:13:26 GMT
• Title: SPARK: Low Latency Single-Camera 3D Pose Estimation for Autonomous Racing using Keypoints
• Abstract summary: We present SPARK, a single-camera pose-estimation algorithm for autonomous racing using keypoint detection.<n>It achieves long-range detection with high accuracy, exceeding the performance of state-of-the-art monocular camera detection algorithms.<n>We evaluate the performance of our approach on real-world autonomous racing data and compare it to state-of-the-art LiDAR and camera detection algorithms.
• Score: 5.912377792360711
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In autonomous racing, fast detection of other participants' movements is required to plan safe, collision-free trajectories with non-cooperative opponents. LiDAR detection is inherently slower and harder to deploy on edge devices than vision methods, causing delayed detections that limit object tracking performance during high-dynamic maneuvering. Utilizing monocular 3D detection enables an easy-to-deploy, low-latency detection of other participants on the racetrack. We present SPARK, a single-camera pose-estimation algorithm for autonomous racing using keypoint detection. It achieves long-range detection with high accuracy, exceeding the performance of state-of-the-art monocular camera detection algorithms while maintaining lower latency. By employing well-optimized YOLO models and leveraging the fixed geometry in the autonomous racing domain, the algorithm also exhibits low latency and resource usage. We evaluate the performance of our approach on real-world autonomous racing data and compare it to state-of-the-art LiDAR and camera detection algorithms. The source code is available at: https://github.com/TUMFTM/SPARK-camera-det

Related papers

• Driving in Spikes: An Entropy-Guided Object Detector for Spike Cameras [62.94986160782233]
  Spike cameras offer microsecond latency and ultra high dynamic range for object detection.<n>Their sparse, discrete output cannot be processed by standard image-based detectors.<n>We propose EASD, an end to end spike camera detector with a dual branch design.<n>We introduce DSEC Spike, the first driving oriented simulated spike detection benchmark.
  arXiv  Detail & Related papers  (2025-11-19T14:16:17Z)
• Real-Time Navigation for Autonomous Aerial Vehicles Using Video [11.414350041043326]
  We introduce a novel Markov Decision Process(MDP) framework to reduce the workload of Computer Vision(CV) algorithms.<n>We apply our proposed framework to both feature-based and neural-network-based object-detection tasks.<n>These holistic tests show significant benefits in energy consumption and speed with only a limited loss in accuracy.
  arXiv  Detail & Related papers  (2025-04-01T01:14:42Z)
• Temporal Correlation Meets Embedding: Towards a 2nd Generation of JDE-based Real-Time Multi-Object Tracking [52.04679257903805]
  Joint Detection and Embedding (JDE) trackers have demonstrated excellent performance in Multi-Object Tracking (MOT) tasks. Our tracker, named TCBTrack, achieves state-of-the-art performance on multiple public benchmarks.
  arXiv  Detail & Related papers  (2024-07-19T07:48:45Z)
• Multi-Object Tracking based on Imaging Radar 3D Object Detection [0.13499500088995461]
  This paper presents an approach for tracking surrounding traffic participants with a classical tracking algorithm. Learning based object detectors have been shown to work adequately on lidar and camera data, while learning based object detectors using standard radar data input have proven to be inferior. With the improvements to radar sensor technology in the form of imaging radars, the object detection performance on radar was greatly improved but is still limited compared to lidar sensors due to the sparsity of the radar point cloud. The tracking algorithm must overcome the limited detection quality while generating consistent tracks.
  arXiv  Detail & Related papers  (2024-06-03T05:46:23Z)
• PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search [64.28335667655129]
  Multiple object tracking is a critical task in autonomous driving. As tracking accuracy improves, neural networks become increasingly complex, posing challenges for their practical application in real driving scenarios due to the high level of latency. In this paper, we explore the use of the neural architecture search (NAS) methods to search for efficient architectures for tracking, aiming for low real-time latency while maintaining relatively high accuracy.
  arXiv  Detail & Related papers  (2024-03-23T04:18:49Z)
• Multi-Object Tracking with Camera-LiDAR Fusion for Autonomous Driving [0.764971671709743]
  The proposed MOT algorithm comprises a three-step association process, an Extended Kalman filter for estimating the motion of each detected dynamic obstacle, and a track management phase. Unlike most state-of-the-art multi-modal MOT approaches, the proposed algorithm does not rely on maps or knowledge of the ego global pose. The algorithm is validated both in simulation and with real-world data, with satisfactory results.
  arXiv  Detail & Related papers  (2024-03-06T23:49:16Z)
• NVRadarNet: Real-Time Radar Obstacle and Free Space Detection for Autonomous Driving [57.03126447713602]
  We present a deep neural network (DNN) that detects dynamic obstacles and drivable free space using automotive RADAR sensors. The network runs faster than real time on an embedded GPU and shows good generalization across geographic regions.
  arXiv  Detail & Related papers  (2022-09-29T01:30:34Z)
• Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Tracking [53.64390261936975]
  We present Minkowski Tracker, a sparse-temporal R-CNN that jointly solves object detection and tracking problems. Inspired by region-based CNN (R-CNN), we propose to track motion as a second stage of the object detector R-CNN. We show in large-scale experiments that the overall performance gain of our method is due to four factors.
  arXiv  Detail & Related papers  (2022-08-22T04:47:40Z)
• CFTrack: Center-based Radar and Camera Fusion for 3D Multi-Object Tracking [9.62721286522053]
  We propose an end-to-end network for joint object detection and tracking based on radar and camera sensor fusion. Our proposed method uses a center-based radar-camera fusion algorithm for object detection and utilizes a greedy algorithm for object association. We evaluate our method on the challenging nuScenes dataset, where it achieves 20.0 AMOTA and outperforms all vision-based 3D tracking methods in the benchmark.
  arXiv  Detail & Related papers  (2021-07-11T23:56:53Z)
• Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device [53.323878851563414]
  We propose a compiler-aware unified framework incorporating network enhancement and pruning search with the reinforcement learning techniques. Specifically, a generator Recurrent Neural Network (RNN) is employed to provide the unified scheme for both network enhancement and pruning search automatically. The proposed framework achieves real-time 3D object detection on mobile devices with competitive detection performance.
  arXiv  Detail & Related papers  (2020-12-26T19:41:15Z)
• Streaming Object Detection for 3-D Point Clouds [29.465873948076766]
  LiDAR provides a prominent sensory modality that informs many existing perceptual systems. The latency for perceptual systems based on point cloud data can be dominated by the amount of time for a complete rotational scan. We show how operating on LiDAR data in its native streaming formulation offers several advantages for self driving object detection.
  arXiv  Detail & Related papers  (2020-05-04T21:55:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.