A brief review and challenges of object detection in optical remote sensing imagery

Abstract

Traditional object detection algorithms and strategies are difficult to meet the requirements of data processing efficiency, performance, speed and intelligence in object detection. Through the study and imitation of the cognitive ability of the brain, deep learning can analyze and process the data features. It has a strong ability of visualization and becomes the mainstream algorithm of current object detection applications. Firstly, we have discussed the developments of traditional object detection methods. Secondly, the frameworks of object detection (e.g. Region-based CNN (R-CNN), Spatial Pyramid Pooling Network (SPP-NET), Fast-RCNN and Faster-RCNN) which combine region proposals and convolutional neural networks (CNNs) are briefly characterized for optical remote sensing applications. You only look once (YOLO) algorithm is the representative of the object detection frameworks (e.g. YOLO and Single Shot MultiBox Detector (SSD)) which transforms the object detection into a regression problem. The limitations of remote sensing images and object detectors have been highlighted and discussed. The feasibility and limitations of these approaches will lead researchers to prudently select appropriate image enhancements. Finally, the problems of object detection algorithms in deep learning are summarized and the future recommendations are also conferred.

Smart Mirror Based Home Automation Using Voice Command and Mobile Application

“…These all three modules interact with the firebase and use firebase to update, store or retrieve data which afterward can be used to update, store or retrieve data in a smart mirror application using the python programming language. Nevertheless, this application can be remarkably improved by using some key image processing approaches [36][37][38].…”

A Novel Eye-Tracking Device Designed with a Head Gesture Control Module

“…The quality of images is the vital aid towards cloud computing and high resolution imagery which is being observed by quality of experience (QoE) [25,26] and quality of service (QoS) [27]; the image quality can also be enhance by using optimal feature assessment technique [28,29] and pre-processing [30][31][32]. Nevertheless, the performance based on image quality is also enhanced with the help of post-processing [33,34] and feature merging methods [35][36][37] . Close infrared light is coordinated towards the focal point of the eyes; causing noticeable disparity in the cornea which is the external optical component of the eye.…”

A novel image clustering method based on coupled convolutional and graph convolutional network

“…First, many authors try to combine mature clustering algorithms with deep learning. For example, network training is combined with k-means goals [15][16][17]. However, a simple combination of clustering and presentation learning methods often leads to regression and resolution.…”