For Solution #5: Custom Object Detection​ on Mobile

A project log for Multi-Domain Depth AI Usecases on the Edge

SLAM, ADAS-CAS, Sensor Fusion, Touch-less Attendance, Elderly Assist, Monocular Depth, Gesture & Security Cam with OpenVINO, Math & RPi

Anand UthamanAnand Uthaman 10/25/2021 at 07:350 Comments

To detect a custom object on mobile, we have followed these steps:

To freeze the model, execute

python models/research/object_detection/ -input_type image_tensor -pipeline_config_path data/ssd_mobilenet_v1_custom.config -trained_checkpoint_prefix <model ckpt path> -output_directory object_detection_graph

To deploy the model on mobile,

I have taken 300 images of household chairs, annotated them, and did the above steps to deploy on Android mobile to prove the concept. See the mobile is able to detect generic chairs in real-time.

                                                        Mobile able to detect custom chairs inside house in real-time