Spatial and Temporal Context Information Fusion Based Flying Objects Detection for Autonomous Sense and Avoid

Zhang, Zhouyu; Cao, Yunfeng; Ding, Meng; Zhuang, Likui; Wang, Zhaoyang

doi:10.1109/icuas.2018.8453295

Cited by 8 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The simulation dataset, called SimUAV in this paper, is generated by simulation platform to alleviate the data-insufficiency further. Both datasets are released on github 1 , where detailed information could be found.…”

Section: Data Generationmentioning

confidence: 99%

“…Therefore, researches on the detection and recognition of UAV small targets has been rapidly growing. Currently, UAV object detection technology is commonly based on deep learning object detection algorithms [1][2] [3]. Although deep learning methods have made great progress in general object detection, some popular detectors such as Fast R-CNN [4], Faster R-CNN [5], SSD [6], YOLO [7], RetinaNet [8] still work poorly in small object detection tasks including UAV detection [9], pedestrian detection [10], traffic sign detection [11], etc.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Approach for UAV Small Object Detection with Simulation-based Transfer Learning and Adaptive Fusion

Rui,

Youwei,

Huafei

et al. 2021

Preprint

View full text Add to dashboard Cite

Precisely detection of Unmanned Aerial Vehicles(UAVs) plays a critical role in UAV defense systems. Deep learning is widely adopted for UAV object detection whereas researches on this topic are limited by the amount of dataset and small scale of UAV. To tackle these problems, a novel comprehensive approach that combines transfer learning based on simulation data and adaptive fusion is proposed. Firstly, the open-source plugin AirSim proposed by Microsoft is used to generate mass realistic simulation data. Secondly, transfer learning is applied to obtain a pre-trained YOLOv5 model on the simulated dataset and fine-tuned model on the real-world dataset. Finally, an adaptive fusion mechanism is proposed to further improve small object detection performance. Experiment results demonstrate the effectiveness of simulation-based transfer learning which leads to a 2.7% performance increase on UAV object detection. Furthermore, with transfer learning and adaptive fusion mechanism, 7.1% improvement is achieved compared to the original YOLO v5 model.

show abstract

Section: Data Generationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Comprehensive Approach for UAV Small Object Detection with Simulation-based Transfer Learning and Adaptive Fusion

Rui,

Youwei,

Huafei

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…After the joint learning process of weight ω = [ω 1 , ω 2 ] and dictionary D, target presence probability of each node i ∈ V could be computed throughout the whole graph via message passing. The computation of message passing can be expressed as (7), where j = 1, 2, 3, 4 indicate four neighbors of each node i.…”

Section: ) the Layered Structure For Extracting Spatial Contextmentioning

confidence: 99%

“…The algorithms for flying targets detection may vary for different sensing devices, and the airborne sensing devices can be divided into two categories, namely non-cooperative and cooperative. The non-cooperative sensing equipment including Light Detection and Ranging (LIDAR) [4], visual sensors [5]- [7], and radar [8] can take effect without exchanging information with the same sensing equipment. While cooperative sensing equipment contains Automatic Dependent Surveillance-Broadcast (ADS-B) [9] and Traffic Alert and Collision Avoidance System (TCAS) [10], which have been widely installed for Detect and Avoid (DAA) systems on manned aircraft.…”

Section: Introductionmentioning

confidence: 99%

Vision-Based Flying Targets Detection via Spatiotemporal Context Fusion

et al. 2019

Self Cite

View full text Add to dashboard Cite

Deriving from the imperative necessities for developing Sense and Avoid (SAA) capability of Unmanned Aerial Vehicle (UAV), a newly designed flying targets detection algorithm is presented in this paper for enhancing the UAV environment perception ability. Since spatiotemporal context is crucial for insuring the effectiveness of flying targets detection, the algorithm is constructed on the basis of spatiotemporal context fusion. The algorithm proposed in this paper contains three parts, namely the spatial context extraction, temporal context extraction and spatiotemporal context fusion. 1) In order to extract spatial context, dense sampling method is firstly applied to obtain dense image grids, then spatial context is generated via pre-learned conditional random field (CRF) model using a layered structure: dense image patches, bottom feature descriptors, sparse codes, and predicted CRF labels. 2) In order to extract temporal context, the forward and back motion history image (FBMHI) is firstly computed for detecting motion cues, and the adaptive foreground and background isolation is further adopted for acquiring the temporal probability map. 3) The presence probability map of flying targets is finally obtained by spatiotemporal context fusion, and flying targets is therefore picked out by analyzing fused presence probability map. A set of videos containing different drone models are selected for evaluation, and the comparisons against other algorithms demonstrate superiority of the proposed algorithm.INDEX TERMS Sense and avoid, spatiotemporal, context fusion, conditional random field, sparse representation, forward and back motion history image.

show abstract

“…achieved object-centric motion stabilization of image patches by a regression-based approach, and then detected flying objects by combining both appearance and motion cues as spatio-temporal image cubes [11,12]. In addition to these, the research of vision-based sense-and-avoid for micro-UAV could provide a reference [13,14].…”

Section: Introductionmentioning

confidence: 99%

Flying Small Target Detection for Anti-UAV Based on a Gaussian Mixture Model in a Compressive Sensing Domain

Wang

Sun

et al. 2019

Sensors

View full text Add to dashboard Cite

Addressing the problems of visual surveillance for anti-UAV, a new flying small target detection method is proposed based on Gaussian mixture background modeling in a compressive sensing domain and low-rank and sparse matrix decomposition of local image. First of all, images captured by stationary visual sensors are broken into patches and the candidate patches which perhaps contain targets are identified by using a Gaussian mixture background model in a compressive sensing domain. Subsequently, the candidate patches within a finite time period are separated into background images and target images by low-rank and sparse matrix decomposition. Finally, flying small target detection is achieved over separated target images by threshold segmentation. The experiment results using visible and infrared image sequences of flying UAV demonstrate that the proposed methods have effective detection performance and outperform the baseline methods in precision and recall evaluation.

show abstract

Spatial and Temporal Context Information Fusion Based Flying Objects Detection for Autonomous Sense and Avoid

Cited by 8 publications

References 19 publications

A Comprehensive Approach for UAV Small Object Detection with Simulation-based Transfer Learning and Adaptive Fusion

A Comprehensive Approach for UAV Small Object Detection with Simulation-based Transfer Learning and Adaptive Fusion

Vision-Based Flying Targets Detection via Spatiotemporal Context Fusion

Flying Small Target Detection for Anti-UAV Based on a Gaussian Mixture Model in a Compressive Sensing Domain

Contact Info

Product

Resources

About