0000000000173852
AUTHOR
Solomon Negussie Tesema
Multi-Grid Redundant Bounding Box Annotation for Accurate Object Detection
Modern leading object detectors are either two-stage or one-stage networks repurposed from a deep CNN-based backbone classifier network. YOLOv3 is one such very-well known state-of-the-art one-shot detector that takes in an input image and divides it into an equal-sized grid matrix. The grid cell having the center of an object is the one responsible for detecting the particular object. This paper presents a new mathematical approach that assigns multiple grids per object for accurately tight-fit bounding box prediction. We also propose an effective offline copy-paste data augmentation for object detection. Our proposed method significantly outperforms some current state-of-the-art object de…
DenseYOLO: Yet Faster, Lighter and More Accurate YOLO
As much as an object detector should be accurate, it should be light and fast as well. However, current object detectors tend to be either inaccurate when lightweight or very slow and heavy when accurate. Accordingly, determining tolerable tradeoff between speed and accuracy of an object detector is not a simple task. One of the object detectors that have commendable balance of speed and accuracy is YOLOv2. YOLOv2 performs detection by dividing an input image into grids and training each grid cell to predict certain number of objects. In this paper we propose a new approach to even make YOLOv2 more fast and accurate. We re-purpose YOLOv2 into a dense object detector by using fine-grained gr…
Towards General Purpose Object Detection: Deep Dense Grid Based Object Detection
Object detection is one of the most challenging and very important branch of computer vision. Some of the challenging aspect of a detection network is the fact that an object can appear anywhere in the image, be partially occluded by another object, might appear in crowd or have greatly varying scales. Consequently, we propose a fine grained and equally spaced dense grid cells throughout an input image be responsible of detecting an object. We re-purpose an already existing deep state-of-the-art detector or classifier into deep and dense detector. Our dense object detector uses binary class encoding and hence suitable for very large multi-class object detector. We also propose a more flexib…
Deep Convolutional Neural Network Based Object Detection Inference Acceleration Using FPGA
Object detection is one of the most challenging yet essential computer vision research areas. It means labeling and localizing all known objects of interest on an input image using tightly fit rectangular bounding boxes around the objects. Object detection, having passed through several evolutions and progressions, nowadays relies on the successes of image classification networks based on deep convolutional neural networks. However, as the depth and complication of convolutional neural networks increased, detection speed reduced, and accuracy increased. Unfortunately, most computer vision applications, such as real-time object tracking on an embedded system, requires lightweight, fast and a…