Accomplishment:
-Compared the specification of Yolov5 and Yolov8, the most recent version of the OR model, and made a decision to continually work on Yolov5. Yolov5 is directly built on PyTorch framework, which can be easily implemented and adjusted to add a distance estimation feature.
-Forked Yolov5 github repository, so that the google collab can use our version of OR model to train a dataset. There was an issue regarding np.int, so changed to int instead to avoid errors.
-Currently looking into an open source of Yolov9 + Dist. Est. feature to upgrade the version of OR model. It will increase the accuracy and reduce the latency while reducing the development time to add a Dist. Est. feature.
Progress:
I am currently working on integrating Yolov5 with Dist. Est. feature, so I am behind schedule. However, since I have found an open source of Yolov9 + Dist. Est. feature, I will be back on schedule and be able to test the OR model by 03/16. To do so, I will need to retrain the Yolov9 model with an indoor object dataset. This will be done by 03/11. The data processor will be implemented by 03/15 to leave a day for the testing of the OR module.
Projected Deliverables:
By 03/11, I will finish retraining the Yolov9 + Dist. Est. feature. Then, by 03/15, I will finish implementing the data processor that outputs a desired result of the closest object, so that the testing can be done by 03/16.