[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images

Fast-BEV: A Fast and Strong Bird’s-Eye View Perception Baseline

Out-of-the-box code and models for CMU's object detection and tracking system for multi-camera surveillance videos. Speed optimized Faster-RCNN model. Tensorflow based. Also supports EfficientDet. WACVW'20

[ICCV 2023] OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction

[CoRL 2022] SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation

This repo contains links to multi-person re-identification and tracking dataset in top view multi-camera environment.

DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation (ICCV 2023)

A Low-cost Open-source High-speed Multi-camera Motion Capture System.

Multi-camera Network research resources

Underwater Dataset for Visual-Inertial Methods and data with transitioning between multiple refractive media.

Official Repo For "RockTrack"

OpenCV Universal Multi thread video Interface with neglectable latency.

A unity package for applying post-processing effects to assembled 2D assets

A flexible video acquisition pipeline for synchronized multi-camera recording, designed for Raspberry Pi systems and adaptable to other Linux-based camera setups.

Real-time multi-camera face tracking system with PyQt5 interface and alert notifications (including Telegram notifications). Supports webcams, RTSP streams, and provides face recognition with InsightFace models.

Summit Vitals: Multi-Camera and Multi-Signal Biosensing at High Altitudes

GUI for viewing and recording with multi camera systems including event cameras.

Central control for video acquisition with (many) Raspberry Pi cameras

A Flask app for multiple live video streaming over a network with object detection, tracking (optional), and counting. Uses YOLO v4 with Tensorflow backend as the object detection model and Deep SORT trained on the MARS dataset for object tracking. Each video stream has an independent thread and uses ImageZMQ for asynchronous sending and process

Multi-camera systems are becoming affordable and intelligent through research and commercial application. However, few resources are available to assist software engineers in developing fully-fledged solutions using such systems. To address this lack of support the project described in this report has developed a software platform that supports …