DeepSORT is one of the most popular object tracking algorithms. It is an extension to Simple Online Real-time Tracker or SORT, which is an online-based tracking algorithm. 

SORT is an algorithm that uses the Kalman filter for estimating the location of the object given the previous location of the same. The Kalman filter is very effective against the occlusions. 

SORT comprises of three components:

  1. Detection: Detecting the object of interest in the initial stage i.  
  2. Estimation: Predicting the future location i+1 of the object from the initial stage using the Kalman filter. It is worth noting that the Kalman filter just approximates the object’s new location, which needs to be optimized. 
  3. Association: As the Kalman filter estimates the future location of the object i+1, it needs to be optimized using the correct position. This is usually done by detecting the position of the object in that position i+1. The problem is solved optimally using the Hungarian algorithm.

With the basics of SORT out of the way, we can incorporate deep learning techniques to enhance the SORT algorithm. Deep neural networks allow SORT to estimate the object’s location with much higher accuracy because these networks can now describe the features of the target image. 

Essentially, the CNN classifier is trained on a task-specific dataset until it achieves good accuracy. Once it is achieved, the classifier is stripped, and we are left with only the features extracted from that dataset. This extracted feature is then incorporated with the SORT algorithm to track objects.