This project presents an advanced computer
vision system for object detection, classification, and
tracking utilizing the cutting-edge YOLOv4 algorithm.
Recent advances in deep learning have led to significant
improvements in the accuracy and speed of object
detection models. The project focuses on training the
YOLOv4 model on large-scale datasets with diverse
object categories. By employing transfer learning
techniques, the model will be fine-tuned to adapt to
specific target objects of interest, achieving a high level of
accuracy and generalization.The Object detection,
classification and tracking model achieves high accuracy
in detecting and tracking objects. The performance
analysis of the system showcases promising results.The fluctuation results due to the model not being
very robust to occlusions. Overall, the model significantly
improves the accuracy of existing model by detecting the
targets that are very close to the edges of the frame to by
focusing on them before they exit the frame. The model
counts the objects and get their position information when
tacking. However, ongoing improvement efforts are
necessary to address potential challenges, such as real
time multi object tracking, object association and
occlusion handling.
Keywords : Yolov4, detection, classification, tracking, OpenCV.