- Metrics to Use to Evaluate Deep Learning Object Detectors - Aug 6, 2020.
It's important to understand which metric should be used to evaluate trained object detectors and which one is more important. Is mAP alone enough to evaluate the objector models? Can the same metric be used to evaluate object detectors on validation set and test set?
- Image Recognition and Object Detection in Retail - Feb 26, 2020.
“According to Gartner, by 2020, 85% of customer interactions in the retail industry will be managed by AI.”
- Pedestrian Detection Using Non Maximum Suppression Algorithm - Dec 17, 2019.
Read this overview of a complete pipeline for detecting pedestrians on the road.
- OpenStreetMap Data to ML Training Labels for Object Detection - Sep 9, 2019.
I am really interested in creating a tight, clean pipeline for disaster relief applications, where we can use something like crowd sourced building polygons from OSM to train a supervised object detector to discover buildings in an unmapped location.
- A 2019 Guide to Object Detection - Aug 1, 2019.
Object detection has been applied widely in video surveillance, self-driving cars, and object/people tracking. In this piece, we’ll look at the basics of object detection and review some of the most commonly-used algorithms and a few brand new approaches, as well.
- An Overview of Human Pose Estimation with Deep Learning - Jun 28, 2019.
Human Pose Estimation is one of the main research areas in computer vision. The reason for its importance is the abundance of applications that can benefit from such a technology. Here's an introduction to the different techniques used in Human Pose Estimation based on Deep Learning.
- Pedestrian Detection in Aerial Images Using RetinaNet - Mar 26, 2019.
Object Detection in Aerial Images is a challenging and interesting problem. By using Keras to train a RetinaNet model for object detection in aerial images, we can use it to extract valuable information.
- Object Detection with Luminoth - Mar 13, 2019.
In this article you will learn about Luminoth, an open source computer vision library which sits atop Sonnet and TensorFlow and provides object detection for images and video.
- People Tracking using Deep Learning - Mar 12, 2019.
Read this overview of people tracking and how deep learning-powered computer vision has allowed for phenomenal performance.
- How to do Everything in Computer Vision - Feb 27, 2019.
The many standard tasks in computer vision all require special consideration: classification, detection, segmentation, pose estimation, enhancement and restoration, and action recognition. Let me show you how to do everything in Computer Vision with Deep Learning!
- The 6 Most Useful Machine Learning Projects of 2018 - Jan 15, 2019.
Let’s take a look at the top 6 most practically useful ML projects over the past year. These projects have published code and datasets that allow individual developers and smaller teams to learn and immediately create value.
- Semantic Segmentation: Wiki, Applications and Resources - Oct 4, 2018.
An extensive overview covering the features of Semantic Segmentation and possible uses for it, including GeoSensing, Autonomous Drive, Facial Recognition and more.
- Data Augmentation For Bounding Boxes: Rethinking image transforms for object detection - Sep 19, 2018.
Data Augmentation is one way to battle this shortage of data, by artificially augmenting our dataset. In fact, the technique has proven to be so successful that it's become a staple of deep learning systems.
Pages: 1 2
- Object Detection and Image Classification with YOLO - Sep 10, 2018.
We explain object detection, how YOLO algorithm can help with image classification, and introduce the open source neural network framework Darknet.
- Analyze a Soccer (Football) Game Using Tensorflow Object Detection and OpenCV - Jul 10, 2018.
For the data scientist within you let's use this opportunity to do some analysis on soccer clips. With the use of deep learning and opencv we can extract interesting insights from video clips
- How to Implement a YOLO (v3) Object Detector from Scratch in PyTorch: Part 1 - May 17, 2018.
The best way to go about learning object detection is to implement the algorithms by yourself, from scratch. This is exactly what we'll do in this tutorial.
- Using Tensorflow Object Detection to do Pixel Wise Classification - Mar 29, 2018.
Tensorflow recently added new functionality and now we can extend the API to determine pixel by pixel location of objects of interest. So when would we need this extra granularity?
- Computer Vision by Andrew Ng - 11 Lessons Learned - Dec 22, 2017.
I recently completed Andrew Ng’s computer vision course on Coursera. In this article, I will discuss 11 key lessons that I learned in the course.
- Object Detection: An Overview in the Age of Deep Learning - Sep 13, 2017.
Like many other computer vision problems, there still isn’t an obvious or even “best” way to approach the problem of object recognition, meaning there’s still much room for improvement.
Pages: 1 2