A publication about Computer Vision and Deep Learning.
Explore recent posts
Depthwise Separable Convolution
Separable Depthwise Convolution In this tutorial, you'd learn about what depthwise separable convolutions are and how they compare to regular convolution filters. You'd see that they are more efficient than regular convolutions in terms of speed and…
Multi-Resolution Image Blending using OpenCV
Multi-Resolution Image Blending This article dives deep into the world of seemlessly merging 2 images together in a more natural way than alpha matting . The techniques used are Laplacian and Gaussian blending. There would be no deep dive into the…
Multiple Object Tracking
Multiple Object Tracking (MOT) involves tracing the motion of an object (or many objects) across frames in a video stream. This is done by maintaining an index of an object or multiple objects and associating the index to the object as it moves…
YOLOv1: You Only Look Once
The You only look once (YOLO) algorithm is the first in a series of 4 iterations of the algorithm. Developed by Joseph Redmon et al, it was the first novel object detection algorithm that performed detection using a unified end-to-end neural network…
Camera Calibration
Camera calibration is an important first topic in 3D computer vision and also in image processing when removing distortion from an image taken with a pinhole camera. It is the process of determining the intrinsic and extrinsic parameters of the…
Image Matting I
Introduction to Image Matting A common problem in imaging, which can be defined as the matting problem, is extracting a foreground subject in an image, usually with the goal of placing the foreground subject in a different image Image matting is the…
Browse the categories
Sign up to my newsletter
I'd notify you when I publish a new article and also write about recent developments in computer vision and deep learning I've come across.