Atsuya Kobayashi
Takumi Inoue
Keisuke Okazaki
Yoriaki Hirota

We developped

• An inference environment for object recognition models using YOLO (v2, v3) (Darknet)
• Sort (non-maximum suppresion) for unique object recognition
• Unique OSC sequencer for playing in CPU environment
• OSC integration with Max/MSP
• MIDI connection between Max and Ableton Live

Sonification program is built with Msx patcher.