XS-VID: An Extremely Small Video Object Detection Dataset

• URL: http://arxiv.org/abs/2407.18137v1
• Date: Thu, 25 Jul 2024 15:42:46 GMT
• Title: XS-VID: An Extremely Small Video Object Detection Dataset
• Authors: Jiahao Guo, Ziyang Xu, Lianjun Wu, Fei Gao, Wenyu Liu, Xinggang Wang,
• Abstract summary: We develop the XS-VID dataset, which comprises aerial data from various periods and scenes, and annotates eight major object categories. To further evaluate existing methods for detecting extremely small objects, XS-VID extensively collects three types of objects with smaller pixel areas. We propose YOLOFT, which enhances local feature associations and integrates temporal motion features, significantly improving the accuracy and stability of SVOD.
• Score: 33.62124448175971
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Small Video Object Detection (SVOD) is a crucial subfield in modern computer vision, essential for early object discovery and detection. However, existing SVOD datasets are scarce and suffer from issues such as insufficiently small objects, limited object categories, and lack of scene diversity, leading to unitary application scenarios for corresponding methods. To address this gap, we develop the XS-VID dataset, which comprises aerial data from various periods and scenes, and annotates eight major object categories. To further evaluate existing methods for detecting extremely small objects, XS-VID extensively collects three types of objects with smaller pixel areas: extremely small (\textit{es}, $0\sim12^2$), relatively small (\textit{rs}, $12^2\sim20^2$), and generally small (\textit{gs}, $20^2\sim32^2$). XS-VID offers unprecedented breadth and depth in covering and quantifying minuscule objects, significantly enriching the scene and object diversity in the dataset. Extensive validations on XS-VID and the publicly available VisDrone2019VID dataset show that existing methods struggle with small object detection and significantly underperform compared to general object detectors. Leveraging the strengths of previous methods and addressing their weaknesses, we propose YOLOFT, which enhances local feature associations and integrates temporal motion features, significantly improving the accuracy and stability of SVOD. Our datasets and benchmarks are available at \url{https://gjhhust.github.io/XS-VID/}.

Related papers

• FADE: A Dataset for Detecting Falling Objects around Buildings in Video [75.48118923174712]
  Falling objects from buildings can cause severe injuries to pedestrians due to the great impact force they exert. FADE contains 1,881 videos from 18 scenes, featuring 8 falling object categories, 4 weather conditions, and 4 video resolutions. We develop a new object detection method called FADE-Net, which effectively leverages motion information.
  arXiv  Detail & Related papers  (2024-08-11T11:43:56Z)
• ESOD: Efficient Small Object Detection on High-Resolution Images [36.80623357577051]
  Small objects are usually sparsely distributed and locally clustered. Massive feature extraction computations are wasted on the non-target background area of images. We propose to reuse the detector's backbone to conduct feature-level object-seeking and patch-slicing.
  arXiv  Detail & Related papers  (2024-07-23T12:21:23Z)
• Visible and Clear: Finding Tiny Objects in Difference Map [50.54061010335082]
  We introduce a self-reconstruction mechanism in the detection model, and discover the strong correlation between it and the tiny objects. Specifically, we impose a reconstruction head in-between the neck of a detector, constructing a difference map of the reconstructed image and the input, which shows high sensitivity to tiny objects. We further develop a Difference Map Guided Feature Enhancement (DGFE) module to make the tiny feature representation more clear.
  arXiv  Detail & Related papers  (2024-05-18T12:22:26Z)
• VirtualPainting: Addressing Sparsity with Virtual Points and Distance-Aware Data Augmentation for 3D Object Detection [3.5259183508202976]
  We present an innovative approach that involves the generation of virtual LiDAR points using camera images. We also enhance these virtual points with semantic labels obtained from image-based segmentation networks. Our approach offers a versatile solution that can be seamlessly integrated into various 3D frameworks and 2D semantic segmentation methods.
  arXiv  Detail & Related papers  (2023-12-26T18:03:05Z)
• MOSE: A New Dataset for Video Object Segmentation in Complex Scenes [106.64327718262764]
  Video object segmentation (VOS) aims at segmenting a particular object throughout the entire video clip sequence. The state-of-the-art VOS methods have achieved excellent performance (e.g., 90+% J&F) on existing datasets. We collect a new VOS dataset called coMplex video Object SEgmentation (MOSE) to study the tracking and segmenting objects in complex environments.
  arXiv  Detail & Related papers  (2023-02-03T17:20:03Z)
• Towards Large-Scale Small Object Detection: Survey and Benchmarks [48.961205652306695]
  We construct two large-scale Small Object Detection dAtasets (SODA), SODA-D and SODA-A, which focus on the Driving and Aerial scenarios respectively. For SODA-A, we harvest 2513 high resolution aerial images and annotate 872069 instances over nine classes. The proposed datasets are the first-ever attempt to large-scale benchmarks with a vast collection of exhaustively annotated instances.
  arXiv  Detail & Related papers  (2022-07-28T14:02:18Z)
• ImpDet: Exploring Implicit Fields for 3D Object Detection [74.63774221984725]
  We introduce a new perspective that views bounding box regression as an implicit function. This leads to our proposed framework, termed Implicit Detection or ImpDet. Our ImpDet assigns specific values to points in different local 3D spaces, thereby high-quality boundaries can be generated.
  arXiv  Detail & Related papers  (2022-03-31T17:52:12Z)
• Tiny Object Tracking: A Large-scale Dataset and A Baseline [40.93697515531104]
  We create a large-scale video dataset, which contains 434 sequences with a total of more than 217K frames. In data creation, we take 12 challenge attributes into account to cover a broad range of viewpoints and scene complexities. We propose a novel Multilevel Knowledge Distillation Network (MKDNet), which pursues three-level knowledge distillations in a unified framework.
  arXiv  Detail & Related papers  (2022-02-11T15:00:32Z)
• TJU-DHD: A Diverse High-Resolution Dataset for Object Detection [48.94731638729273]
  Large-scale, rich-diversity, and high-resolution datasets play an important role in developing better object detection methods. We build a diverse high-resolution dataset (called TJU-DHD) The dataset contains 115,354 high-resolution images and 709,330 labeled objects with a large variance in scale and appearance.
  arXiv  Detail & Related papers  (2020-11-18T09:32:24Z)

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.