IndoorCrowd: A Multi-Scene Dataset for Human Detection, Segmentation, and Tracking with an Automated Annotation Pipeline

• URL: http://arxiv.org/abs/2604.02032v1
• Date: Thu, 02 Apr 2026 13:38:31 GMT
• Title: IndoorCrowd: A Multi-Scene Dataset for Human Detection, Segmentation, and Tracking with an Automated Annotation Pipeline
• Abstract summary: IndoorCrowd is a dataset for indoor human detection, instance segmentation, and multi-object tracking.<n>It comprises $31$ videos with human-verified, per-instance segmentation masks.
• Score: 39.799207552858114
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding human behaviour in crowded indoor environments is central to surveillance, smart buildings, and human-robot interaction, yet existing datasets rarely capture real-world indoor complexity at scale. We introduce IndoorCrowd, a multi-scene dataset for indoor human detection, instance segmentation, and multi-object tracking, collected across four campus locations (ACS-EC, ACS-EG, IE-Central, R-Central). It comprises $31$ videos ($9{,}913$ frames at $5$fps) with human-verified, per-instance segmentation masks. A $620$-frame control subset benchmarks three foundation-model auto-annotators: SAM3, GroundingSAM, and EfficientGroundingSAM, against human labels using Cohen's $κ$, AP, precision, recall, and mask IoU. A further $2{,}552$-frame subset supports multi-object tracking with continuous identity tracks in MOTChallenge format. We establish detection, segmentation, and tracking baselines using YOLOv8n, YOLOv26n, and RT-DETR-L paired with ByteTrack, BoT-SORT, and OC-SORT. Per-scene analysis reveals substantial difficulty variation driven by crowd density, scale, and occlusion: ACS-EC, with $79.3\%$ dense frames and a mean instance scale of $60.8$px, is the most challenging scene. The project page is available at https://sheepseb.github.io/IndoorCrowd/.

Related papers

• Zero-Shot Object Re-Identification in Egocentric Kitchen Videos via Multi-Stage SAM3 Feature Fusion [59.32099847726022]
  We study zero-shot object ReID on the EPIC-Kitchens benchmark.<n>The goal is to match active food and kitchen-tool instances across frames using only pre-trained visual features.
  arXiv  Detail & Related papers  (2026-05-25T23:01:41Z)
• Efficient Multi-View 3D Object Detection by Dynamic Token Selection and Fine-Tuning [16.27181704006191]
  Existing multi-view 3D object detection approaches widely adopt large-scale pre-trained vision transformer (ViT)-based foundation models as backbones.<n>We propose an image token compensator combined with a token selection for ViT backbones to accelerate multi-view 3D object detection.
  arXiv  Detail & Related papers  (2026-04-15T07:44:01Z)
• 3D-Aware Instance Segmentation and Tracking in Egocentric Videos [107.10661490652822]
  Egocentric videos present unique challenges for 3D scene understanding. This paper introduces a novel approach to instance segmentation and tracking in first-person video. By incorporating spatial and temporal cues, we achieve superior performance compared to state-of-the-art 2D approaches.
  arXiv  Detail & Related papers  (2024-08-19T10:08:25Z)
• Matching Anything by Segmenting Anything [109.2507425045143]
  We propose MASA, a novel method for robust instance association learning. MASA learns instance-level correspondence through exhaustive data transformations. We show that MASA achieves even better performance than state-of-the-art methods trained with fully annotated in-domain video sequences.
  arXiv  Detail & Related papers  (2024-06-06T16:20:07Z)
• View-Consistent Hierarchical 3D Segmentation Using Ultrametric Feature Fields [52.08335264414515]
  We learn a novel feature field within a Neural Radiance Field (NeRF) representing a 3D scene. Our method takes view-inconsistent multi-granularity 2D segmentations as input and produces a hierarchy of 3D-consistent segmentations as output. We evaluate our method and several baselines on synthetic datasets with multi-view images and multi-granular segmentation, showcasing improved accuracy and viewpoint-consistency.
  arXiv  Detail & Related papers  (2024-05-30T04:14:58Z)
• DIVOTrack: A Novel Dataset and Baseline Method for Cross-View Multi-Object Tracking in DIVerse Open Scenes [74.64897845999677]
  We introduce a new cross-view multi-object tracking dataset for DIVerse Open scenes with dense tracking pedestrians. Our DIVOTrack has fifteen distinct scenarios and 953 cross-view tracks, surpassing all cross-view multi-object tracking datasets currently available. Furthermore, we provide a novel baseline cross-view tracking method with a unified joint detection and cross-view tracking framework named CrossMOT.
  arXiv  Detail & Related papers  (2023-02-15T14:10:42Z)
• Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Tracking [20.66906781151]
  In multi-object tracking, the tracker maintains in its memory the appearance and motion information for each object in the scene. Many approaches model each target in isolation and lack the ability to use all the targets in the scene to jointly update the memory. We propose a training strategy adapted to multi-track pooling which generates hard tracking episodes online.
  arXiv  Detail & Related papers  (2021-01-28T18:12:39Z)
• IA-MOT: Instance-Aware Multi-Object Tracking with Motion Consistency [40.354708148590696]
  "instance-aware MOT" (IA-MOT) can track multiple objects in either static or moving cameras. Our proposed method won the first place in Track 3 of the BMTT Challenge in CVPR 2020 workshops.
  arXiv  Detail & Related papers  (2020-06-24T03:53:36Z)

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.