In the resent years machine learning has being applied to various arias of agriculture. Machine learning (ML) plays a crucial role in addressing weed-related issues in agriculture.  ML algorithms, particularly those based on deep learning, can learn intricate patterns and features, making them well-suited for the nuanced task of weed detection. In the present research deep learning algorithms such as YOLOv5 and SORT are adapted and applied to detect and to track vegetables and weeds based on computer vision. First, datasets of annotated full color images of cabbage and weed are created. Then, the ML algorithm YOLOv5 for object detection is selected. It detects and localize objects in a frame in real time from video. Next, YOLOv5 is trained to detect cabbage and weed form our annotated datasets. The accuracy of the model performance is studied. The real-time tracking algorithm SORT is selected and adjusted to track cabbages and weeds from videos. SORT is a high – speed, accurate and robust tracking algorithm. Moreover, the object tracker SORT is adjusted to assign to each vegetable and weed unique number. Finally, the modified object detector and tracker provide significant information about the distribution, sizes and numbers of weeds and vegetables in the given areas. This lead to efficient weed treatment procedure.