Autonomous driving is the way to go forward.
Here is my article based on some of the work we have done in this field.
- Python-tensorflow based deep learning model for object classification trained on a novel data-set
- Trained and deployed on an embedded computing platform for real-time object detection
Python based object classification model trained on a self made data-set using tensorflow and deployed on an embedded computing platform for real time data transfer to the driver
Special purpose object detection systems need to be fast, accurate and dedicated to classifying a handful but relevant number of objects. Our aim was to integrate a system which utilizes the Inception’s vast heuristically mapped image pre-diction tree along-with a real time system accurate and robust enough to work at various processing powers and give the user enough confidence of identifying and detecting object with a single frame. As this property can be utilized at huge number of places relying on real time detection, it might not be limited to only driving assistance or autonomous driving systems, but are beyond the scope of this project.
To come up with a novel dataset, which would have an image tree with enough weights and variety so as to predict the objects being identified with high accuracy and precision, was taken up to set up the softmax layer of Inception, which was earlier weighted by the existing ImageNet dataset. The results were a convincing recognition accuracy and prediction confidence with real time test frames of a video. There is also a growing concern about pedestrian safety with the advent of autonomous vehicles. That has also been tackled using a real time single frame pedestrian identifier with satisfactory accuracy. With our algorithm, we intend to make a significant contribution in this field as we propose a driver assistant system which integrates object detection and security which can help improve road safety and contribute to the growing demand in the domain of autonomous and intelligent driver assist systems in vehicles.
In our work, we propose an algorithm which can be applied to create an intelligent driver assistant system. The algorithm was implemented in two phases and the following sections shall describe the implementation of each phase of the algorithm. This project also extends into a sub-section that describes the Autonomous Security and Surveillance System which involves a vehicle classifier used to identify the type of a vehicle and also a license plate recognition system in order to capture and store the registration number of a vehicle. It also has a section dedicated to describe our real-time object detection system which is used to identify common on-road objects in every video frame.
Read more here.