First Place Solution to the ECCV 2024 ROAD++ Challenge @ ROAD++ Spatiotemporal Agent Detection 2024

• URL: http://arxiv.org/abs/2410.23077v1
• Date: Wed, 30 Oct 2024 14:52:43 GMT
• Title: First Place Solution to the ECCV 2024 ROAD++ Challenge @ ROAD++ Spatiotemporal Agent Detection 2024
• Authors: Tengfei Zhang, Heng Zhang, Ruyang Li, Qi Deng, Yaqian Zhao, Rengang Li,
• Abstract summary: The task of Track 1 is agent detection, which aims to construct an "agent tube" for agents in consecutive video frames. Our solutions focus on the challenges in this task including extreme-size objects, low-light, imbalance and fine-grained classification. We rank first in the test set of Track 1 for the ROAD++ Challenge 2024, and achieve 30.82% average video-mAP.
• Score: 12.952512012601874
• License:
• Abstract: This report presents our team's solutions for the Track 1 of the 2024 ECCV ROAD++ Challenge. The task of Track 1 is spatiotemporal agent detection, which aims to construct an "agent tube" for road agents in consecutive video frames. Our solutions focus on the challenges in this task, including extreme-size objects, low-light scenarios, class imbalance, and fine-grained classification. Firstly, the extreme-size object detection heads are introduced to improve the detection performance of large and small objects. Secondly, we design a dual-stream detection model with a low-light enhancement stream to improve the performance of spatiotemporal agent detection in low-light scenes, and the feature fusion module to integrate features from different branches. Subsequently, we develop a multi-branch detection framework to mitigate the issues of class imbalance and fine-grained classification, and we design a pre-training and fine-tuning approach to optimize the above multi-branch framework. Besides, we employ some common data augmentation techniques, and improve the loss function and upsampling operation. We rank first in the test set of Track 1 for the ROAD++ Challenge 2024, and achieve 30.82% average video-mAP.

Related papers

• DeTra: A Unified Model for Object Detection and Trajectory Forecasting [68.85128937305697]
  Our approach formulates the union of the two tasks as a trajectory refinement problem. To tackle this unified task, we design a refinement transformer that infers the presence, pose, and multi-modal future behaviors of objects. In our experiments, we observe that ourmodel outperforms the state-of-the-art on Argoverse 2 Sensor and Open dataset.
  arXiv  Detail & Related papers  (2024-06-06T18:12:04Z)
• ODTFormer: Efficient Obstacle Detection and Tracking with Stereo Cameras Based on Transformer [12.58804521609764]
  ODTFormer is a Transformer-based model to address both obstacle detection and tracking problems. We report comparable accuracy to state-of-the-art obstacle tracking models while requiring only a fraction of their cost.
  arXiv  Detail & Related papers  (2024-03-21T17:59:55Z)
• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection [54.92703325989853]
  We propose a two-stage Activation-to-Saliency (A2S) framework that effectively generates high-quality saliency cues. No human annotations are involved in our framework during the whole training process. Our framework reports significant performance compared with existing USOD methods.
  arXiv  Detail & Related papers  (2021-12-07T11:54:06Z)
• Oriented R-CNN for Object Detection [61.78746189807462]
  This work proposes an effective and simple oriented object detection framework, termed Oriented R-CNN. In the first stage, we propose an oriented Region Proposal Network (oriented RPN) that directly generates high-quality oriented proposals in a nearly cost-free manner. The second stage is oriented R-CNN head for refining oriented Regions of Interest (oriented RoIs) and recognizing them.
  arXiv  Detail & Related papers  (2021-08-12T12:47:43Z)
• 2nd Place Solution for Waymo Open Dataset Challenge - Real-time 2D Object Detection [26.086623067939605]
  In this report, we introduce a real-time method to detect the 2D objects from images. We leverage accelerationRT to optimize the inference time of our detection pipeline. Our framework achieves the latency of 45.8ms/frame on an Nvidia Tesla V100 GPU.
  arXiv  Detail & Related papers  (2021-06-16T11:32:03Z)
• An Efficient Approach for Anomaly Detection in Traffic Videos [30.83924581439373]
  We propose an efficient approach for a video anomaly detection system which is capable of running at the edge devices. The proposed approach comprises a pre-processing module that detects changes in the scene and removes the corrupted frames. We also propose a sequential change detection algorithm that can quickly adapt to a new scene and detect changes in the similarity statistic.
  arXiv  Detail & Related papers  (2021-04-20T04:43:18Z)
• Enhancing Object Detection for Autonomous Driving by Optimizing Anchor Generation and Addressing Class Imbalance [0.0]
  This study presents an enhanced 2D object detector based on Faster R-CNN that is better suited for the context of autonomous vehicles. The proposed modifications over the Faster R-CNN do not increase computational cost and can easily be extended to optimize other anchor-based detection frameworks.
  arXiv  Detail & Related papers  (2021-04-08T16:58:31Z)
• Anchor-free Small-scale Multispectral Pedestrian Detection [88.7497134369344]
  We propose a method for effective and efficient multispectral fusion of the two modalities in an adapted single-stage anchor-free base architecture. We aim at learning pedestrian representations based on object center and scale rather than direct bounding box predictions. Results show our method's effectiveness in detecting small-scaled pedestrians.
  arXiv  Detail & Related papers  (2020-08-19T13:13:01Z)
• One-Shot Object Detection without Fine-Tuning [62.39210447209698]
  We introduce a two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module. We also propose novel training strategies that effectively improve detection performance. Our method exceeds the state-of-the-art one-shot performance consistently on multiple datasets.
  arXiv  Detail & Related papers  (2020-05-08T01:59:23Z)

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.