SIMULTANEOUS CONTRAST RESTORATION AND OBSTACLES DETECTION FOR DRIVING ASSISTANCE

Project Title

SIMULTANEOUS CONTRAST RESTORATION AND OBSTACLES DETECTION FOR DRIVING ASSISTANCE

Project Area of Specialization Electrical/Electronic EngineeringProject Summary

This project describes a visio based platform for real-life indoor and outdoor object detection for driving assistance in bad weather conditions, as the visibility decreases exponentially with distance in bad weather conditions, which makes the fog one of the dangerous conditions for driving, to overcome these challenges a smart device is need to be introduced which may detect an object and restore the contrast in Bad weather conditions (fog, haze, rain). From past results and research studies on obstacle detection and contrast restoration, it is found Radar has greater efficiency for obstacle detection and novel de hazing/ fog removal is the best approach for de hazing/ fog removal. The application is developed using Python and functions from OpenCV library and, ultimately ported upon Raspberry PI3 or advanced platform. Template Matching is selected as method. More precisely, a multi-scale version approach is proposed to reduce the processing time and also to extend the detection distance range for accurate traffic sign recognition in indoor/outdoor environment, using OpenCV library of Python. 

Project Objectives

This project four objectives will be covered

1. To detect an Obstacle under the adverse weather conditions with the help of Radar.
2. To remove the foggy, hazy aspects from the detected images using the image processing applications.
3. To restore the Contrast and colors by using filling colors and finding the contours of images.
4. To assist the driver by using LCD monitor display

Project Implementation Method

Obstacle detection

                                    Reliable obstacles detection under adverse weather conditions, especially foggy conditions the classical approaches relying on pattern recognition techniques or points of interest matching are not so efficient anymore hence we propose the novel approach which is able to simultaneously restore the contrast of the scene and to detect the presence of obstacles by stereovision once the atmosphere opacity is known. For capturing of an image in adverse conditions usually IR Camera is preferred and for detection of an object LIDAR and Car Detection RADAR are mostly taken into the consideration because of their better efficiency and accuracy among the other sensors.

• Removal of foggy, hazy aspects

                                             Fog removal and correction are two different parts. Fog removal technique calculates the depth input of an image and enhancement of the depth calculated image is done. The enhanced images are restored with colors. In fog correction method, the images are translated to the HSV color space to get transmission map by applying color correction algorithms.

• Contrast and colors restoration

                                                     We introduce a novel algorithm and variants for visibility restoration from a single image. The main advantage of the proposed algorithm compared with other is its speed. Its complexity is a linear function of the number of image pixels only. This speed allows visibility restoration to be applied for the first time within real-time processing applications such as sign, lane-marking and obstacle detection from an in-vehicle camera. Another advantage is the possibility to handle both color images and gray level images.

Driving Assistance

The role of ADAS is to prevent deaths and injuries by reducing the number of car accidents and the serious impact of those that cannot be avoided, in this context we would like to use LCD monitor and buzzer for the indication of drivers.

Benefits of the Project

This project mainly deals with driving assistance bad weather conditions in order to avoid the road accidents, upon completion of project drivers will not only be assisted by alarming of buzzers but they will be able to see the vehicle near to them as well which will be performed by IR Camera for capturing videos., apart from that this project will let the drivers that how for another vehicle is and what speed the vehicle has currently. This project can also be used deployed for air space as well but keeping in mind that the radar and IR Camera will be required of large ranges.

Technical Details of Final Deliverable

This project will be deployed on the one of the famous programming language Python using the approach of machine learning and artificial intelligence. The functions from OpenCV library and, ultimately ported upon Raspberry PI3 or advanced platform. Template Matching is selected as method. More precisely, a multi-scale version approach is proposed to reduce the processing time and also to extend the detection distance range for accurate traffic sign recognition in indoor/outdoor environment, using OpenCV library of Python

Final Deliverable of the Project HW/SW integrated systemCore Industry TransportationOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Industry, Innovation and Infrastructure, Climate ActionRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	65000
IR Camera	Equipment	1	24000	24000
Car detection radar	Equipment	1	12000	12000
lcd	Equipment	1	5000	5000
raspberrypi	Equipment	1	24000	24000