Skip to content

orange

A high-performance, GPU-accelerated multi-camera capture, streaming and recording application for Emergent Vision GigE cameras.

gui

Overview

orange is built for high-throughput, time-synchronized multi-camera recording. Encoding is GPU-accelerated and scales with the number of GPUs in the host. PTP keeps cameras aligned to sub-frame precision, and a multi-host architecture (one GUI host coordinating any number of headless cam_server nodes over ENet) lets a recording rig scale beyond what a single machine can drive — both in camera count and aggregate pixel rate. Optional TensorRT-based YOLO detection runs on the live streams when a model is provided.

Source on GitHub

Video demo

Features

  1. Multiple cameras streaming
  2. PTP synchronization
  3. GPU accelerated encoding (h264, hevc)
  4. Support mono and color Emergent cameras
  5. Multi-host capture (one GUI host coordinating several headless cam_server nodes)

Performance

Encoding performance using a single A6000 GPU with 7MP Emergent cameras:

encoding benchmark

orange distributes per-camera encoding across GPUs (assigned by gpu_id in each camera's config), so total throughput scales with the number of GPUs in the host — adding GPUs is the recommended path to more cameras or higher resolutions.

Where to start