StackFlow AI Platform
Devices & Quick Start
Models
Qwen3
DeepSeek-R1
Applications
CV Vision Application
Vision Language Model (VLM)
Large Language Model (LLM)
Voice Assistant
BoxDemo
BoxDemo is a multi-channel video detection demo officially provided by AXERA. It supports simultaneous encoding and decoding of up to 16 video streams, and performs detection of motor vehicles, non-motor vehicles, pedestrians, and license plates, with output via HDMI0. AI Pyramid can be used as a multi-channel video computing box.
- Manually download the test videos and upload them to AI Pyramid, or obtain them using the following command.
wget https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/linux/AI_Pyramid/boxvideos.zipTip
If zip is not installed, use apt install zip to install it.
unzip boxvideos.zip
rm boxvideos.zip- Replace the configuration files
cp boxvideos/run.sh /opt/bin/BoxDemo/
cp boxvideos/box.conf /opt/bin/BoxDemo/- Run
Tip
If other programs load and use other AI models, it may cause the program initialization to fail.
/opt/bin/BoxDemo/run.shWait for the program to finish loading. HMDI0 will output multi-channel detection video streams and detection results.