Vue and Machine Learning – Real-time object detection and classification based on Yolo Model created on Darknet

I’d like present solution regarding application Deep Machine Learning on  Vue framework in case of Real-time object detection and classification based on Yolo Model (read more) created on Darknet(Darknet & Yolo) .

Darknet is an open source neural network framework written in C and CUDA. It is fast, easy to install, and supports CPU and GPU computation. You can find the source on GitHub or you can read more about what Darknet can do right here: https://pjreddie.com/darknet/ [1]

YOLOv3 is extremely fast and accurate. In mAP measured at .5 IOU YOLOv3 is on par with Focal Loss but about 4x faster. Moreover, you can easily tradeoff between speed and accuracy simply by changing the size of the model, no retraining required![1]

Comparison to Other Detectors (source: https://pjreddie.com/darknet/yolo/)

Performance on the COCO Dataset (https://pjreddie.com/darknet/yolo/)

How It Yolo Works

Prior detection systems repurpose classifiers or localizers to perform detection. They apply the model to an image at multiple locations and scales. High scoring regions of the image are considered detections.[1]

Yolo uses a totally different approach. It apply a single neural network to the full image. This network divides the image into regions and predicts bounding boxes and probabilities for each region. These bounding boxes are weighted by the predicted probabilities.[1]

Yolo model has several advantages over classifier-based systems. It looks at the whole image at test time so its predictions are informed by global context in the image. It also makes predictions with a single network evaluation unlike systems like R-CNN which require thousands for a single image. This makes it extremely fast, more than 1000x faster than R-CNN and 100x faster than Fast R-CNN. See Yolo paper for more details on the full system [1]

The presented solution has many advantages:
1. Real-time object detection and classification
2. It works on all browsers and is written in pure javascript and vue.
3. Uses live video streaming and is not limited by different kind of web browsers
4. An arbitrary time interval is set, thanks to which we take pictures every n-seconds.

Sources:

[1] Darknet: https://pjreddie.com/darknet/yolo/