You will get State of the Art Access system based on Computer Vision
Project details
You will get an access control system code. So you can save the images of the people you want to give access to. The code will save them and give access to only those people whose images are saved.
Machine Learning Tools
NumPy, OpenCV, PythonWhat's included $120
These options are included with the project scope.
$120
- Delivery Time 2 days
- Number of Revisions 2
- Number of Model Variations 0
- Number of Scenarios 2
- Number of Graphs/Charts 1
- Data Source Connectivity
- Source Code
Optional add-ons
You can add these on the next page.
Additional Scenario
(+ 2 Days)
+$50About Sagar
AI software Developer with experience in DL,CV and ML
New Delhi, India - 5:03 pm local time
I have led several high-impact projects where I am currently working:
Computer Vision System Development: I have spearheaded the creation of computer vision systems for robotic cotton harvesters and robotic apple pickers. My work involved implementing deep learning models for real-time object detection and localization using Intel RealSense cameras (415i, 435i). These systems have significantly enhanced the accuracy and efficiency of the harvesting process.
Autonomous Navigation System: I engineered an autonomous navigation system for these harvesters, enabling them to operate independently within crop rows.
Productionization of Deep Learning Models: I have deployed deep learning models to the endpoints of Intel RealSense cameras, ensuring robust edge computing capabilities for real-time processing in field conditions. This deployment improved the performance and reliability of the vision systems in diverse environmental conditions. This made the usage of various configurations of jetson boards.
MLops Pipelines and CICD: I am responsible for creating and managing MLops pipelines on Azure Databricks, ensuring continuous integration and deployment (CICD) of deep learning models. I also established monitoring systems for real-time model performance tracking, facilitating rapid iteration and improvement.
Structured and Unstructured Data Modeling: I have developed machine learning models for both structured and unstructured data, addressing a variety of business needs. This included creating models for object detection, image segmentation, and data analysis, tailored to the specific requirements of agricultural machinery.
In-House Auto-Annotation Tool: I have designed and implemented an in-house auto-annotation tool for object detection, which streamlined the data labeling process and improved the efficiency of model training.
Fuel Optimization: I have analyzed the fueling behavior of methane-powered tractors, leading to the optimization of tractor fuel capacity. This project involved the creation of a proof of concept (POC) that was presented to senior management, demonstrating significant potential for operational cost savings. This used Azure Data bricks.
Previously, at Bosch Global Software Technologies, I worked on Automated Driving Assistance Systems (ADAS), where I focused on visualizing large-scale data, creating data ingestion pipelines, and enhancing the accuracy of sign classification algorithms. I have also worked as a freelancer, developing AI models for deepfakes and rash driving detection.
In my earlier roles, including at Nayan Technologies and Valiant Communications, I developed AI-based lane violation systems and worked on emotion recognition and pain intensity detection using advanced computer vision techniques.
I hold an M.Tech degree from IIIT-Delhi, with a thesis on Unsupervised Cross Modality Person Re-Identification using CycleGANs and OpenPose. My research contributions, published in IEEE Xplore and Springer, cover topics such as emotion detection, pain intensity detection, and facial feature recognition.
Skills: Azure Databricks, Python, MATLAB, Pandas, Numpy, TensorFlow, PyTorch, Keras, Scikit-learn, OpenCV, OpenPose, GANs, CycleGANs, Docker, Google Cloud Computing (GCP), Azure Machine Learning, MLops, SQL, Power BI, Anaconda, Databricks, Git, MATLAB, Flask, RNN, ANN, CNN, LSTM, HCI, IoT, Object Detection, Medical Imaging, Digital Image Processing, Pattern Recognition, Statistical Signal Processing, Multimedia Security, Deep Learning, Advanced Machine Learning, Data Science, Data Analysis, Windows, Ubuntu, Linux.
Steps for completing your project
After purchasing the project, send requirements so Sagar can start the project.
Delivery time starts when Sagar receives requirements from you.
Sagar works on your project following the steps below.
Revisions may occur after the delivery date.
I can hand over the available code that I made.
Any required changes can be done to the existing code.