Object detection systems and methods including an object detection model using a tailored training dataset

An object detection method for use by an object detection system, comprising:

• receiving a first image frame from a region of interest (ROI) detection model that is configured to detect an object in an image and generate an ROI boundary around the object, wherein the first image frame comprises a first ROI boundary around a first object;
• receiving, from the ROI detection model, a second image frame that is a subsequent frame to the first image frame in a video;
• predicting, using an ROI tracking model, that the first ROI boundary will be present in the second image frame in response to detecting the first object in the second image frame, wherein the ROI tracking model is configured to identify objects in an image that are bounded by ROI boundaries and detect whether the objects exist in another image;
• detecting whether the first ROI boundary is present in the second image frame;
• determining that the second image frame should be added to a training dataset for the ROI detection model in response to detecting that the ROI detection model did not generate the first ROI boundary in the second image frame as predicted;
• and
• re-training the ROI detection model, to define a re-trained ROI detection model, using the training dataset comprising the second image frame in response to determining that the second image frame should be added to the training dataset.

A non-transitory computer-readable medium storing instructions for object detection, executable by a processor to:

• receive a first image frame from a region of interest (ROI) detection model that is configured to detect an object in an image and generate an ROI boundary around the object, wherein the first image frame comprises a first ROI boundary around a first object;
• receive, from the ROI detection model, a second image frame that is a subsequent frame to the first image frame in a video;
• predict, using an ROI tracking model, that the first ROI boundary will be present in the second image frame in response to detecting the first object in the second image frame, wherein the ROI tracking model is configured to identify objects in an image that are bounded by ROI boundaries and detect whether the objects exist in another image;
• detect whether the first ROI boundary is present in the second image frame;
• determine that the second image frame should be added to a training dataset for the ROI detection model in response to detecting that the ROI detection model did not generate the first ROI boundary in the second image frame as predicted;
• and
• re-train the ROI detection model, to define a re-trained ROI detection model, using the training dataset comprising the second image frame in response to determining that the second image frame should be added to the training dataset.