At the end of Term 1 — Udacity’s SDCND
I have recently completed Term 1 of my Udacity’s Self-Driving Car Nano-degree (SDCND) program and I thought this would be a great time to share the updates on the same. Find below the details of my projects, learnings and milestones related to SDCND program. I am greatly thankful to the almighty God, my sponsors who helped me fund this program, Udacity’s staff, my classmates and every person who directly or indirectly help me succeed in this program and complete the Term 1 so graciously.
- Projects I have worked upon:
Videos: You can checkout the video of complete project by clicking on the Youtube URLs of individual projects. There is also a sound track added to the videos so make sure to watch the videos with speakers on, you will definitely enjoy it.
P.S.: You must and must watch all the videos to have a better experience about these cool projects.
Code Base: The entire code base of every project is committed to my Github account in the respective repositories for detailed reference of the work done. The Github URLs are also provided along with Youtube URLs for the reference. Feel free to check it out and provide your valuable inputs on the same.
Project Advanced Lane Finding: Built an advanced lane-finding algorithm using distortion correction, image rectification, color & perspective transform, gradient thresholding, and sliding window search. Identified lane curvature and vehicle displacement. Overcame environmental challenges such as shadows and pavement changes.
Youtube URL: https://www.youtube.com/watch?v=wXXGlo3Z_S8
Project Vehicle Detection and Tracking: Created a vehicle detection and tracking pipeline with OpenCV, Histogram of Oriented Gradients (HOG), and Support Vector Machines (SVM). Optimized and evaluated the model on video data from an automotive camera taken during highway driving.
Youtube URL: https://www.youtube.com/watch?v=UoZTPs6JhQA
Youtube URL: https://www.youtube.com/watch?v=_2-3DBsX8GE
Project Traffic Sign Classification: Built and trained a deep neural network to classify traffic signs, using Tensorflow. Experimented with different network architectures like LeNet, AlexNet, VGG, GoogLenet, ResNet. Performed image pre-processing and validation to guard against overfitting.
2. Skills / Technologies I have learned:
The following infographic illustrates almost all the concepts, skills and frameworks I have learned so far as a part of Computer Vision and Deep Learning skills in the first term of Udacity’s Self-Driving Car Nano-degree program. Although, there are so many great things which I have learned in this program and it’s not possible to capture all of it in a single infographic.
I will be learning about Sensor Fusion, Kalman Filters, Localization, Particle Filter, Perception, Control Systems, PID and Linear Quadratic Regulator used in Autonomous Vehicles as part of my term 2 curriculum.
The modules are created in collaboration with Industry partners Mercedes Benz and Uber-ATG (Advanced Technologies Group).
3. Milestones achieved so far:
- Successfully completed Term 1
- Got two interview calls for SDC job profile based on the skills learnt in the program
- Started a small Artificial Intelligence Community in my current organization to share knowledge and make developers aware of these cutting-edge technologies.
- Will commence Term 2 in the month of July.
Please feel free to share your valuable insights, thoughts and feedbacks.