Object Detection

Object detection is a technology that lies under the broader domain of Computer Vision. This technology is capable of identifying objects that exist in images and videos and tracking them. It has various applications like face recognition, vehicle recognition, pedestrian counting, self-driving vehicles, security systems, and a lot more.

YOLO (You Only Look Once) is an object detection algorithm that allows to detect objects in an image in near real-time. YOLOv4 is the 4th version of YOLO which was introduced in April 2020. It treats object detection as a regression problem, taking a given input image and simultaneously learning bounding box coordinates and corresponding class label probabilities. We can easily detect objects in our image/ video using YOLOv4.

Stack (OS & PL & FW)

Windows

Python/ C++

Darknet/ YOLOv4

OpenCV

Dataset

COCO dataset

Open Images Dataset v6 (OID)

Custom Images dataset (2000 imgs/ class)

Hardware (Resources) (Storage & Compute Power & Time)

Nvidia RTX GPU Needed

Can run almost at real time with a high end device

Workflow (Processing)

Image Data collection

Image labelling

Image preprocessing

Training dataset on pretrained model

Training results

End To End (Development & Integration in a System)

Image Data collection

Image labelling

Image preprocessing

Training dataset on pretrained model

Training results

Model deployment

Model maintenance

Deployment (Server / API)

Desktop app

Flask web app

Applications (General Real World Use)

There are many applications of object detection. One of the famous applications is face detection and recognition. Some of the main applications of object detection techniques are given in the following list.

Optical Character recognition: OCR is the recognition of hand-written, printed, or typed characters from an image. These techniques are used for scanning printed books to a digital document. Other applications are data entry, traffic sign recognition, etc.

Self-driving cars: These cars can drive by themselves. One of the major capabilities of self-driving cars is detecting pedestrians, cars, trucks, traffic signs, etc. These detections are essential for the proper working of self-driving cars.

Verification using face and IRIS code: Face and IRIS verification and authentication are used in iPhone and Android phones. It does the device authorization if the exact face or IRIS match is detected.

Robotics: There are a lot of applications in robotics using object detection. One of the common applications is bin picking and sorting of objects. Using object detection techniques, the robot is able to understand the location of objects. Using that information, the robot is able to pick the object and is able to sort it.

Object tracking and counting: Using object detection techniques, you can track an object and can be used as an object counter. For example, how many cars have crossed in a junction, how people entered a shopping mall etc.

Use Case (Our Specific)

We trained the model on a custom dataset of TV, monitor and laptop screens. Our model was able to detect all screens available in the frame. Then using image processing we were able to replace the screen image with our own image or video.