Object Detection Part 1: R-CNN, Sliding Window and Selective Search

Описание: This is the first video in the object detection series and in it we are exploring the definition of object detection in computer vision, how we can approach this task using the sliding window algorithm and how the Region-based Convolutional Neural Network (R-CNN) model improves this approach by employing the selective search region proposal algorithm.

References
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
"Rich feature hierarchies for accurate object detection and semantic segmentation" paper: https://arxiv.org/abs/1311.2524
"Selective Search for Object Recognition" paper: http://www.huppelen.nl/publications/s...
Selective search algorithm (more details): https://learnopencv.com/selective-sea...

Related Videos
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Object Detection Part 2: Fast R-CNN, Region Projection and Region of Interest (RoI) Pooling Layer:    • Object Detection Part 2: Fast R-CNN, Regio...  
Object Detection Part 3: Faster R-CNN, Region Proposal Network and Intersection over Union:    • Object Detection Part 3: Faster R-CNN, Reg...  
Why Neural Networks Can Learn Any Function:    • Why Neural Networks Can Learn Any Function  
Why Deep Neural Networks (DNNs) Underperform Tree-Based Models on Tabular Data:    • Why Deep Neural Networks (DNNs) Underperfo...  
Why Residual Connections (ResNet) Work:    • Why Residual Connections (ResNet) Work  

Contents
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
00:00 - Intro
00:14 - Object Detection Definition
00:59 - Sliding Window
02:00 - R-CNN Model
02:32 - Selective Search Algorithm
04:27 - Cons of Using R-CNN
05:20 - Outro

Follow Me
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
🐦 Twitter: @datamlistic   / datamlistic  
📸 Instagram: @datamlistic   / datamlistic  
📱 TikTok: @datamlistic   / datamlistic  

Channel Support
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
The best way to support the channel is to share the content. ;)

If you'd like to also support the channel financially, donating the price of a coffee is always warmly welcomed! (completely optional and voluntary)
► Patreon:   / datamlistic  
► Bitcoin (BTC): 3C6Pkzyb5CjAUYrJxmpCaaNPVRgRVxxyTq
► Ethereum (ETH): 0x9Ac4eB94386C3e02b96599C05B7a8C71773c9281
► Cardano (ADA): addr1v95rfxlslfzkvd8sr3exkh7st4qmgj4ywf5zcaxgqgdyunsj5juw5
► Tether (USDT): 0xeC261d9b2EE4B6997a6a424067af165BAA4afE1a

#cnn #rcnn #objectdetection #selectivesearch