Vision-Based Detection and Distance Estimation of Micro Unmanned Aerial Vehicles

Gökçe, Fatih; Üçoluk, Göktürk; Şahi̇n, Erol; Kalkan, Sinan

doi:10.3390/s150923805

Cited by 100 publications

(37 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Systems have been designed for environmental monitoring, search and rescue, mapping, and mining and post seismic emergency management [1,2,3,4,5]. In order to obtain an acceptable cost/benefit ratio of these systems, there have been many techniques to reduce the cost including the aspects of the sensor, the platform, and the algorithm [6].…”

Section: Introductionmentioning

confidence: 99%

An Improved Multi-Sensor Fusion Navigation Algorithm Based on the Factor Graph

Zeng

Chen

Liu

et al. 2017

Sensors

View full text Add to dashboard Cite

An integrated navigation system coupled with additional sensors can be used in the Micro Unmanned Aerial Vehicle (MUAV) applications because the multi-sensor information is redundant and complementary, which can markedly improve the system accuracy. How to deal with the information gathered from different sensors efficiently is an important problem. The fact that different sensors provide measurements asynchronously may complicate the processing of these measurements. In addition, the output signals of some sensors appear to have a non-linear character. In order to incorporate these measurements and calculate a navigation solution in real time, the multi-sensor fusion algorithm based on factor graph is proposed. The global optimum solution is factorized according to the chain structure of the factor graph, which allows for a more general form of the conditional probability density. It can convert the fusion matter into connecting factors defined by these measurements to the graph without considering the relationship between the sensor update frequency and the fusion period. An experimental MUAV system has been built and some experiments have been performed to prove the effectiveness of the proposed method.

show abstract

Section: Introductionmentioning

confidence: 99%

An Improved Multi-Sensor Fusion Navigation Algorithm Based on the Factor Graph

Zeng

Chen

Liu

et al. 2017

Sensors

View full text Add to dashboard Cite

show abstract

“…Due to the drawbacks of IPM, it would fail in cases that objects are located over 40 meters apart or on a curved road. Another vision-based distance estimation work [13] learned a support vector machine regressor to predict an object-specific distance given the width and height of a bounding box. DistNet [14] was a recent try to build a network for distance estimation, where the authors utilized a CNN-based model (YOLO) for bounding boxes prediction instead of the image features learning for distance estimation.…”

Section: Related Workmentioning

confidence: 99%

“…Similar to the recent work [13], we compute the width and height of each bounding box in the training subset, and train a SVR with the ground truth distance. After that, we get the estimated distances for objects in the validation set by feeding the widths and heights of their bounding boxes into the trained SVR.…”

Section: Compared Approachesmentioning

confidence: 99%

Learning Object-Specific Distance From a Monocular Image

Zhu

Fang

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Environment perception, including object detection and distance estimation, is one of the most crucial tasks for autonomous driving. Many attentions have been paid on the object detection task, but distance estimation only arouse few interests in the computer vision community. Observing that the traditional inverse perspective mapping algorithm performs poorly for objects far away from the camera or on the curved road, in this paper, we address the challenging distance estimation problem by developing the first end-toend learning-based model to directly predict distances for given objects in the images. Besides the introduction of a learning-based base model, we further design an enhanced model with a keypoint regressor, where a projection loss is defined to enforce a better distance estimation, especially for objects close to the camera. To facilitate the research on this task, we construct the extented KITTI and nuScenes (mini) object detection datasets with a distance for each object. Our experiments demonstrate that our proposed methods outperform alternative approaches (e.g., the traditional IPM, SVR) on object-specific distance estimation, particularly for the challenging cases that objects are on a curved road. Moreover, the performance margin implies the effectiveness of our enhanced method.

show abstract

“…Additionally, the safety of the technology and its potential for accidents are viewed with increasing scepticism. However, important efforts are being dedicated to develop sense and avoid technologies (Gökçe et al 2015;Yu and Zhang 2015;Mcfadyen and Mejias 2016), and there is much interest to establish clear legislation. Other limitations of the UAV technology for monitoring infrastructure are technical aspects like the need for specialist expertise, the lack of standards and an insufficiently developed range of image analysis techniques (Kelcey and Lucieer 2012;Laliberte et al 2011).…”

Section: Advantages and Limitations Of Small Uavs For Monitoring Pipementioning

confidence: 99%

Small unmanned airborne systems to support oil and gas pipeline monitoring and mapping

Gómez

Green

2017

Arab J Geosci

View full text Add to dashboard Cite

Oil and gas transmission pipelines require monitoring for maintenance and safety, to prevent equipment failure and accidents. Unmanned aerial vehicles (UAVs) technology is emerging as an opportunity to supplement current monitoring systems. Small UAV technological solutions are flexible and adaptable and with a demonstrated capacity to obtain valuable data at small to medium spatial scales. Systematic surveys of extensive areas are better completed with fixed-wing platforms and automatic flight design, whilst multirotor platforms provide flexibility in shorter and localized inspection missions. The type of sensor carried by an aerial platform determines the sort of data acquired and the obtainable information; sensors also determine the need for specific mechanical designs and the provision of energy on-board required from the system. UAV systems prototyped to monitor pipelines are reviewed in this paper, and a number of monitoring scenarios are proposed and illustrated. Notwithstanding difficulties encountered in the generalization of use for civilian applications, small UAVs have demonstrated, through research and operational cases, the capacity to support the inspection and monitoring of oil and gas pipelines.

show abstract

Vision-Based Detection and Distance Estimation of Micro Unmanned Aerial Vehicles

Cited by 100 publications

References 79 publications

An Improved Multi-Sensor Fusion Navigation Algorithm Based on the Factor Graph

An Improved Multi-Sensor Fusion Navigation Algorithm Based on the Factor Graph

Learning Object-Specific Distance From a Monocular Image

Small unmanned airborne systems to support oil and gas pipeline monitoring and mapping

Contact Info

Product

Resources

About