Search for: All records

Underwater image enhancement is often perceived as a disadvantageous process to object detection. We propose a novel analysis of the interactions between enhancement and detection, elaborating on the potential of enhancement to improve detection. In particular, we evaluate object detection performance for each individual image rather than across the entire set to allow a direct performance comparison of each image before and after enhancement. This approach enables the generation of unique queries to identify the outperforming and underperforming enhanced images compared to the original images. To accomplish this, we first produce enhanced image sets of the original images using recent image enhancement models. Each enhanced set is then divided into two groups: (1) images that outperform or match the performance of the original images and (2) images that underperform. Subsequently, we create mixed original-enhanced sets by replacing underperforming enhanced images with their corresponding original images. Next, we conduct a detailed analysis by evaluating all generated groups for quality and detection performance attributes. Finally, we perform an overlap analysis between the generated enhanced sets to identify cases where the enhanced images of different enhancement algorithms unanimously outperform, equally perform, or underperform the original images. Our analysis reveals that, when evaluated individually, most enhanced images achieve equal or superior performance compared to their original counterparts. The proposed method uncovers variations in detection performance that are not apparent in a whole set as opposed to a per-image evaluation because the latter reveals that only a small percentage of enhanced images cause an overall negative impact on detection. We also find that over-enhancement may lead to deteriorated object detection performance. Lastly, we note that enhanced images reveal hidden objects that were not annotated due to the low visibility of the original images. 

Abstract In recent years, deep learning has significantly reshaped numerous fields and applications, fundamentally altering how we tackle a variety of challenges. Areas such as natural language processing (NLP), computer vision, healthcare, network security, wide-area surveillance, and precision agriculture have leveraged the merits of the deep learning era. Particularly, deep learning has significantly improved the analysis of remote sensing images, with a continuous increase in the number of researchers and contributions to the field. The high impact of deep learning development is complemented by rapid advancements and the availability of data from a variety of sensors, including high-resolution RGB, thermal, LiDAR, and multi-/hyperspectral cameras, as well as emerging sensing platforms such as satellites and aerial vehicles that can be captured by multi-temporal, multi-sensor, and sensing devices with a wider view. This study aims to present an extensive survey that encapsulates widely used deep learning strategies for tackling image classification challenges in remote sensing. It encompasses an exploration of remote sensing imaging platforms, sensor varieties, practical applications, and prospective developments in the field. 

Deep learning (DL) algorithms have achieved significantly high performance in object detection tasks. At the same time, augmented reality (AR) techniques are transforming the ways that we work and connect with people. With the increasing popularity of online and hybrid learning, we propose a new framework for improving students’ learning experiences with electrical engineering lab equipment by incorporating the abovementioned technologies. The DL powered automatic object detection component integrated into the AR application is designed to recognize equipment such as multimeter, oscilloscope, wave generator, and power supply. A deep neural network model, namely MobileNet-SSD v2, is implemented for equipment detection using TensorFlow’s object detection API. When a piece of equipment is detected, the corresponding AR-based tutorial will be displayed on the screen. The mean average precision (mAP) of the developed equipment detection model is 81.4%, while the average recall of the model is 85.3%. Furthermore, to demonstrate practical application of the proposed framework, we develop a multimeter tutorial where virtual models are superimposed on real multimeters. The tutorial includes images and web links as well to help users learn more effectively. The Unity3D game engine is used as the primary development tool for this tutorial to integrate DL and AR frameworks and create immersive scenarios. The proposed framework can be a useful foundation for AR and machine-learning-based frameworks for industrial and educational training. 

Ensuring software security is a critical task for a deliverable software system in today’s world, and its proper implementation guarantees the quality and security of the information ingested, stored, and processed by the system. It is imperative to introduce computer science and computer engineering students (CS/CE) with the secure software design practices early in their curriculum. This approach will help them understand fundamentals of secure programming, vulnerabilities in software systems, and secure software development before joining the industry workforce. In this paper, we propose an educational framework that integrates software security concepts in a software engineering design course. We envision that the framework will engage CS/CE students applying security principles and practices in different phases of the software development life cycle (SDLC) process. Our work focuses on review of common security requirements, policies, and mechanisms related to specific use cases as well as how those requirements are defined during the software design. 

Recent studies have shown that fringe-adjusted joint transform correlation (FJTC) can be effectively applied for single class and even multiclass object detection in hyperspectral imagery (HSI). However, directly utilizing FJTC based techniques for HSI processing may not be efficient due to the fact that HSI may contain a large volume of data redundancy. Therefore, incorporating dimensionality reduction (DR) methods prior to the object detection procedure is suggested. In this paper, we combine several DRs individually with class-associative spectral FJTC (CSFJTC), and then compare their performance on single class and multiclass object detection tasks using a real-world hyperspectral data set. Test results show that the CSFJTC with denoising autoencoder provides superior performance compared to the alternate methods for detecting few dissimilar patterns in the scene.