Content deleted Content added
Changing short description from "small object detection" to "Detecting small objects in digital images" |
Citation bot (talk | contribs) Add: bibcode, pages, volume. Removed URL that duplicated identifier. | Use this bot. Report bugs. | Suggested by Headbomb | Linked from Wikipedia:WikiProject_Academic_Journals/Journals_cited_by_Wikipedia/Sandbox | #UCB_webform_linked 480/967 |
||
| (23 intermediate revisions by 11 users not shown) | |||
Line 1:
{{Short description|Detecting small objects in digital images}}
'''Small object detection''' is a particular case of [[object detection]] where various techniques are employed to detect small objects in digital images and videos.
== Uses ==
[[File:Track_Results.webm|thumb|An example of object tracking]]
== Problems with small objects ==
* Modern-day object detection algorithms such as [[You Only Look Once
* Sometimes, the shadow of an object is detected as a part of object itself.<ref>{{Cite
* At present, [[Unmanned aerial vehicle|drones]] are very widely used in aerial imagery.<ref>{{Cite
[[File:Disp_shadow.jpg|thumb|Shadow and drone movement effect|alt=Here, both images are from same video. See, How the shadow of objects affecting detection accuracy. Also, drone's self-movement changes the scene near boundary(Refer to object "car" at bottom-left corner).]]
== Methods ==
Various methods<ref>{{Cite
[[File:Yolov5 (Ariel top view of Ahmedabad, Gujarat, India, 2022).jpg|thumb|YOLOv5 detection result]]
[[File:
[[File:Yolov7 (Ariel top view of Ahmedabad, Gujarat, India, 2022).jpg|thumb|YOLOv7 detection output
=== Improvising existing techniques ===
Line 25:
==== Choosing a data set that has small objects ====
The [[machine learning]] model's output depends on
==== Generating more data via augmentation, if required ====
[[Deep learning]] models have billions of neurons that settle down to some weights after training. Therefore, it requires a good amount of quantitative and qualitative data for better training.<ref>{{Cite web |title=The Size and Quality of a Data Set {{!}} Machine Learning |url=https://developers.google.com/machine-learning/data-prep/construct/collect/data-size-quality |access-date=2022-09-14 |website=Google Developers |language=en}}</ref> [[Data augmentation]] is useful technique to generate more diverse data<ref name=":0" /> from an existing data set.
==== Increasing image capture resolution and model’s input resolution ====
These help to get more features from objects and eventually learn the best from them. For example, a bike object in the 1280 X 1280 [[Image resolution|resolution]] image has more features than the 640 X 640 resolution.
==== Auto learning anchors ====
Selecting anchor size plays a vital role in small object detection.<ref>{{
==== Tiling approach during training and inference ====
State-of-the-art object detectors allow only the fixed size of image and
==== Feature Pyramid Network (FPN) ====
Use a feature [[Pyramid (image processing)|pyramid]] network<ref>{{
=== Add-on techniques ===
Instead of modifying existing methods, some add-on techniques are there, which can be directly placed on top of existing approaches to detect smaller objects. One such technique is Slicing Aided Hyper Inference(SAHI).<ref>{{
=== Well-Optimised techniques for small object detection ===
Various deep learning techniques are available that focus on such object detection problems
== Other applications ==
* Crowd counting<ref>{{Cite
* Vehicle re-identification<ref>{{Cite journal |
* Animal detection<ref>{{Cite
* Fish detection<ref>{{Cite
== See also ==
Line 66:
== External links ==
* [https://github.com/VisDrone/VisDrone-Dataset VisDrone] dataset by AISKYEYE team at Lab of Machine Learning and Data Mining, Tianjin University, China.
{{Computer vision}}
[[Category:
[[Category:Imaging]]
| |||