-
VidGear
- VidGear is a High-Performance Framework that provides an all-in-one complete Video Processing solution for building real-time applications in python. VidGear provides an easy-to-use, highly extensible, Multi-Threaded + Asyncio wrapper around many state-of-the-art specialized libraries like OpenCV, FFmpeg, ZeroMQ, picamera, starlette, pafy and python-mss at its backend, and enable us to flexibly exploit their internal parameters and methods, while silently delivering robust error-handling and unparalleled real-time performance.
-
GitHub
-
TAUGV-UGV
- TAUGV-CSR stands for “Tactically Assisted Unmanned Ground Vehicle with Crawling Surveillance Robot”, can provide remote surveillance and maneuver capabilities in a variable topography. The project consists of an Unmanned Ground Vehicle (UGV) and an attached Crawling Surveillance Robot (CSR)
- Overview
-
Manav Humanoid
- Manav is an autonomous Artificial Intelligence driven Robot with human body structure, behavior (biomechanics) and replicates human cognition. Cognition involves developing computational models of human behavior and improving it over the period of time. It interacts with the external environment using its prodigious Natural Language Processing Engine and a state-of-the-art Artificial Intelligence perception enhanced by various internal Deep-Learning and Computer Vision Algorithms.
- Overview
-
KropiT - AI powered Face Cropper
- KropiT (formally known as PiciT) is your everyday use app. Either you want a great DP for your social media account or a quick passport-size photo, this app will come in handy to get you the image of the desired dimension and quality. Just add your gallery of images and start cropping faces immediately. Our AI-powered App helps you do your job faster by generating Cropped and perfectly Aligned Faces from the image just by CLICKING A BUTTON!
- Try it
-
Matson: The talking AI
- The Idea behind creating Matson was to able to integrate various present-day Deep-Learning and Computer Vision algorithms in Jasper(i.e. an open source platform for developing always-on, voice-controlled applications and your own virtual voice assistant on Raspberry Pi) to make a hybrid of three major AI domains i.e. Speech Recognition, Deep learning, and Computer Vision all at one place so as to achieve human brain like capabilities on any existing hardware that requires onboard intelligence involving learning, recognizing, processing and executing complex deliberate responses in real-time. It made exclusively for Internet of Things connected devices with memory constraints(such as Raspberry Pi), and was created in the first place so as to able to embed it on any existing system/hardware that requires onboard intelligence on the go.
- Overview
-
MeshFlow Controlled Video Stabilization
- This was a research project, where I re-implemented a state-of-the-art Video Stabilization method completely from scratch in python using OpenCV & scientific libraries such as NumPy, Scipy etc., and it uses a novel MeshFlow motion model. The MeshFlow is a spatial smooth sparse motion field with motion vectors only at the mesh vertexes. The proposed method handles spatially-variant motions robustly and its performance is somewhat compareable to YouTube's Video Stabilization. It offers a great potential for a variety of Computer Vision applications such as security systems, robotics, UAVs, etc.
- Overview
-
Raspberry Pi GCC Cross & Native Compilers
- Automated CLI Bash Scripts to produce precompiled Raspberry pi GCC Cross & Native Compilers Binaries/Toolchains, which can be used as a native compilers for Raspberry Pi with full C++17, Or can be used as the Cross-Compiler on any Linux System to compile memory exhustive programs for Raspberry Pi Machine.
-
SourceForge
-
OpenCV+TBB for Raspberry Pi
- Fastest Optimized OpenCV for Rpi3 : Latest pre-compiled binary of Pre-released & Stable OpenCV (4.0.0) along with TBB (2018-Update 6) for the Raspberry Pi.
- GitHub
