Locating objects in images (a.k.a., detection) quickly and efficiently enables object tracking and counting applications on embedded visual sensors (fixed and mobile). By 2012, progress on techniques for detecting objects in images – a topic of perennial interest in computer vision – had plateaued, and techniques based on histogram of oriented gradients (HOG) were state of the art. Soon, though, convolutional neural networks (CNNs), in addition to classifying objects, were also beginning to become effective at simultaneously detecting objects. Research in CNN-based object detection was jump-started by the groundbreaking region-based CNN (R-CNN). We’ll follow the evolution of neural network algorithms for object detection, starting with R-CNN and proceeding to Fast R-CNN, Faster R-CNN, DzYou Only Look Oncedz (YOLO), and up to the latest Single Shot Multibox detector. In this talk, we’ll examine the successive innovations in performance and accuracy embodied in these algorithms – which is a good way to understand the insights behind effective neural-network-based object localization.
Auro Tripathy founded ShatterLine Labs (2015) to apply the growing body of knowledge in Neural Networks to real-world machine-vision problems. A practitioner of deep learning techniques, he focuses on object detection applications using convolutional and recurrent nets.
Below is the video of online session lecture.Written on April 22nd , 2017 by