State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully-convolutional network that simultaneously predicts object bounds and objectness scores at each position. RPNs are trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection.

Last month, NVIDIA unleashed the next-generation edge computing hardware device branded as Jetson AGX Orin at GTC. Courtesy of Nvidia, I was fortunate enough to get a Jetson AGX Orin Developer Kit to evaluate and experiment with it. The Jetson AGX Orin Developer Kit has everything you need to run AI inference at the edge with ultra-low latency and high throughput. As a successor to the most powerful Jetson AGX Xavier, AGX Orin packs a punch. The developer kit comes with a carrier board that makes it easy to connect various peripherals. The Jetson AGX Orin Developer Kit comes with a preview of JetPack SDK 5.0, which is based on the Ubuntu 20.04 root filesystem and Linux Kernel 5.10.

Object detection plays an important role in self-driving cars for security development. However, mobile systems on self-driving cars with limited computation resources lead to difficulties for object detection. To facilitate this, we propose a compiler-aware neural pruning search framework to achieve high-speed inference on autonomous vehicles for 2D and 3D object detection. The framework automatically searches the pruning scheme and rate for each layer to find a best-suited pruning for optimizing detection accuracy and speed performance under compiler optimization. Our experiments demonstrate that for the first time, the proposed method achieves (close-to) real-time, 55ms and 99ms inference times for YOLOv4 based 2D object detection and PointPillars based 3D detection, respectively, on an off-the-shelf mobile phone with minor (or no) accuracy loss.

In my last article I showed you how to do image classification in the browser. Image classification can be a very useful tool, it can give us an idea of what's in an image. However, sometimes we want more. It can be a little counterintuitive, but just because a machine learning model can tell what's in an image, doesn't mean it can tell us where it is in the image. We need a different architecture for that.

In this article, we'll be learning the following: Object detection can be defined as a branch of computer vision which deals with the localization and the identification of an object. Object localization and identification are two different tasks that are put together to achieve this singular goal of object detection. Object localization deals with specifying the location of an object in an image or a video stream, while object identification deals with assigning the object to a specific label, class, or description. With computer vision, developers can flexibly do things like embed surveillance tracking systems for security enhancement, real-time crop prediction, real-time disease identification/ tracking in the human cells, etc. The TensorFlow Model Zoo is a collection of pre-trained object detection architectures that have performed tremendously well on the COCO dataset. The model zoo can be found here.

State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully-convolutional network that simultaneously predicts object bounds and objectness scores at each position. RPNs are trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection.

A Computer Science Engineer who is passionate about AI and all related technologies. He is someone who loves to stay updated with the Tech-revolutions that AI brings in.

With the emergence of onboard vision processing for areas such as the internet of things (IoT), edge computing and autonomous robots, there is increasing demand for computationally efficient convolutional neural network (CNN) models to perform real-time object detection on resource constraints hardware devices. Tiny-YOLO is generally considered as one of the faster object detectors for low-end devices and is the basis for our work. Our experiments on this network have shown that Tiny-YOLO can achieve 0.14 frames per second(FPS) on the Raspberry Pi 3 B, which is too slow for soccer playing autonomous humanoid robots detecting goal and ball objects. In this paper we propose an adaptation to the YOLO CNN model named xYOLO, that can achieve object detection at a speed of 9.66 FPS on the Raspberry Pi 3 B. This is achieved by trading an acceptable amount of accuracy, making the network approximately 70 times faster than Tiny-YOLO. Greater inference speed-ups were also achieved on a desktop CPU and GPU. Additionally we contribute an annotated Darknet dataset for goal and ball detection.

Now, you might be wondering – why is object detection required? ANd more to the point, why do we need to perform real-time object detection?

Researchers have been studying the possibilities of giving machines the ability to distinguish and identify objects through vision for years now. This particular domain, called Computer Vision or CV, has a wide range of modern-day applications. From being used by autonomous cars for object detection on roads to complex facial and body language recognitions that can identify possible crimes or criminal activities, CV has numerous uses in today's world. There is no denying the fact that Object Detection is also one of the coolest applications of Computer Vision. Modern-day CV tools can easily implement object detection on images or even on live stream videos.