Proceedings of the 12th International Conference on Distributed Smart Cameras 2018
DOI: 10.1145/3243394.3243692
|View full text |Cite
|
Sign up to set email alerts
|

Efficient ConvNet-based Object Detection for Unmanned Aerial Vehicles by Selective Tile Processing

Abstract: Many applications utilizing Unmanned Aerial Vehicles (UAVs) require the use of computer vision algorithms to analyze the information captured from their on-board camera. Recent advances in deep learning have made it possible to use single-shot Convolutional Neural Network (CNN) detection algorithms that process the input image to detect various objects of interest. To keep the computational demands low these neural networks typically operate on small image sizes which, however, makes it di cult to detect small… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
32
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
5
3

Relationship

3
5

Authors

Journals

citations
Cited by 59 publications
(32 citation statements)
references
References 9 publications
0
32
0
Order By: Relevance
“…In particular, when a high resolution image is resized there is a significant loss of information, where the pixels representing Fig. 5: Comparison between predictions using DroNet [36] with STP [53] (Left) and Resizing (Right).…”
Section: A Selective Data Processing During Inferencementioning
confidence: 99%
See 2 more Smart Citations
“…In particular, when a high resolution image is resized there is a significant loss of information, where the pixels representing Fig. 5: Comparison between predictions using DroNet [36] with STP [53] (Left) and Resizing (Right).…”
Section: A Selective Data Processing During Inferencementioning
confidence: 99%
“…To this end, we proposed a Selective Tile Processing (STP) [53] approach where the input image is separated into smaller regions, called tiles, in order to avoid resizing the input image and to maintain the object resolution. Given an input image and the DNN input, the number of tiles are extracted and are uniformly distributed across the input image while maintaining a constant overlap between the tiles.…”
Section: Tiny-yolov3mentioning
confidence: 99%
See 1 more Smart Citation
“…Recent research has proposed pushing cropped overlapping tiles of the input image through the CNN independently, without degrading the initial resolution [20] [21] [22]. However, this approach introduces notable computational overhead that can only be partly alleviated by the use of attention and memory mechanisms for selective tile processing [23].…”
Section: B Efficient Learning-based Detectors On Uavsmentioning
confidence: 99%
“…This task can only be performed by the UAV's camera. Next, the two central parts of this application follow; the power transmission lines detection process, and a convolutional neural network (CNN) based approach [8] for the power tower detection process. The final task is responsible to display the results to the ground operator, therefore, it can only be executed on the ground station.…”
Section: A Case Study: Uav-based Power Lines Inspectionmentioning
confidence: 99%