Two novel gesture-based Human-UAV Interaction (HUI) systems are proposed to launch and control a UAV in real-time utilizing a monocular camera and a ground computer. The first proposal is an end-to-end static Gesture-Based Interaction (GBI) system based on classifying the interacted user poses while discarding the gesture interpreting component to boost the system performance up to 99 % with a speed of 28 fps. On the other hand, the second proposal is a dynamic one that adopts a simple model to detect three parts (face and two hands) of the interacted person and tracks them for a certain number of frames till a specific dynamic gesture is recognized. The proposed dynamic method is efficient, decreases the complexity, and speeds the interaction up to 27 fps comparing with the recent multimodel ones. Its backbone is a simplified Tiny-You Only Look Once (YOLO) network saves the resources and speeds the detection process up to 120 fps. Moreover, a comprehensive new gestures dataset was established to facilitate the learning process and aid the research work. A comparative study is carried out to show the performance and efficiency of the proposed dynamic HUI system in terms of detection accuracy and speed with the baseline detector on the human gesture public dataset. Finally, a non-expert volunteer examines the proposed HUIs by launching and driving a Bebop 2 micro UAV through a set of real flights.
Condition assessment of concrete bridge decks using nondestructive evaluation (NDE) technologies concentrates on the assessment of corrosion, delamination and concrete quality. Various NDE technologies can be used for this purpose. To expedite the da
18 April 2022 in International Journal of Remote Sensing
Recently, there has been renewed interest in object detection in computer vision. Several attempts have been made to improve small objects recognition, particularly in aerial images, due to their weak representative features and low resolution. However, these instances are still a challenge. The principal objective of this paper is to introduce a Fused RetinaNet detector, an enhanced RetinaNet with a novel context fusion module instead of the feature pyramid network (FPN), to improve low layers semantic information and top layers spatial resolution. This module firstly aggregates multi-scale backbone feature maps at once to make a robust shallow layer. Then, a parallel-branch dilated module is proposed in front of each network level to present more context information. Finally, aggregation and dilated modules are laterally connected at each backbone level via a bottom-up path approach to compensate for information loss during downsampling. Comprehensive experiments are carried out on NWPU VHR-10 and DOTA aerial image datasets. The evaluation reveals the proposed Fused RetinaNet superiority in aerial images small target detection. It achieves a mean average precision (mAP) value of 91.83% and 57.13% on NWPU VHR-10 and DOTA, respectively. Also, it scores a mAP of 62.59% on DOTA when the k-means clustering algorithm is used.
Aircraft tracking in aerial videos is a challenge due to the small size and appearance affinity with other targets. Recently, the tracking‐by‐detection trackers, such as simple online and realtime tracking (SORT), attracted the attention of many researchers due to the great evolution in deep learning‐based object detectors. SORT depends on motion cues in solving the data association problem by matching high‐score detection bounding boxes to tracklets. However, motion cues are insufficient to track occluded or similar aircraft efficiently. In addition, most occluded aircrafts have a low‐confidence percentage. The main objective of this paper is to propose an F‐SORT tracker, an enhanced SORT tracker with the following improvements. Firstly, fused RetinaNet for small aerial targets is used as a detection framework to boost the detectability of SORT. Then, aircraft appearance features are extracted from the shallowest prediction layer and utilized as additional cues to improve the data association algorithm. Finally, the extracted features distinguish aircraft online from backgrounds via a K‐nearest neighbour classifier. Experiments on an airport dataset show that F‐SORT can significantly improve aircraft tracking. F‐SORT outperforms other state‐of‐the‐art trackers, achieving 72.75%, 59.63%, and 82.89% on MOTA, HOTA, and IDF1. In addition, F‐SORT classifying algorithm boosts other trackers when applied.
Linear frequency modulation (LFM) signals are pivotal in radar systems, enabling high-resolution measurements and target detection. However, these signals are often degraded by noise, significantly impacting their processing and interpretation. Traditional denoising methods, including wavelet-based techniques, have been extensively used to address this issue, yet they often fall short in terms of optimizing performance due to fixed parameter settings. This paper introduces an innovative approach by combining wavelet denoising with long short-term memory (LSTM) networks specifically tailored for LFM signals in radar systems. By generating a dataset of LFM signals at various signal-to-noise Ratios (SNR) to ensure diversity, we systematically identified the optimal wavelet parameters for each noisy instance. These parameters served as training labels for the proposed LSTM-based architecture, which learned to predict the most effective denoising parameters for a given noisy LFM signal. Our findings reveal a significant enhancement in denoising performance, attributed to the optimized wavelet parameters derived from the LSTM predictions. This advancement not only demonstrates a superior denoising capability but also suggests a substantial improvement in radar signal processing, potentially leading to more accurate and reliable radar detections and measurements. The implications of this paper extend beyond modern radar applications, offering a framework for integrating deep learning techniques with traditional signal processing methods to optimize performance across various noise-dominated domains.