Improving object counting in aerial images with density-based threshold shifting

ABSTRACT

This paper presents an approach to reduce the negative effects of object density when objects are counted via detection in aerial images. A novel image dataset was generated and used to fine-tune an existing object detection architecture. A novel video dataset was also generated and used for the development and testing of the proposed approach. The datasets consist of aerial images and videos of sheep with scenarios of tightly clustered and isolated individuals. This ensures both sparse and dense object distributions within our dataset. The proposed approach is compared to a proven detection-based counting baseline. In this work, it is explicitly shown that object density and classification probability have a linearly inverse relationship and that reductions in classification probabilities, caused by high densities, has a significantly negative impact on counting performance. The proposed approach uses density-based threshold shifting to improve counting performance, i.e. by dynamically adjusting the counting threshold, based on the density, we are able to improve counting performance. The proposed approach reduces the overall mean absolute error by 78.51% compared to the baseline on an unseen test dataset. It seamlessly integrates with most existing object detection or instance segmentation frameworks without any modifications. The proposed approach also reduces the sensitivity of the counting threshold selection, implying that competitive results can be achieved with minimal tuning. The code is made publicly available.¹

KEYWORDS:

• Aerial photography
• segmentation
• dense objects

Nomenclature

DREN	=	Difficult Region Estimation Network
FP	=	False Positive
HTC	=	Hybrid Task Cascade
IoU	=	Intersection over Union
KDE	=	Kernel Density Estimation
LDTS	=	Local Density Threshold Shifting
MAE	=	Mean Absolute Error
mAP	=	mean Average Precision

Disclosure statement

No potential conflict of interest was reported by the authors.

Data availability statement

The data that support the findings of this study are available from the corresponding author, R. P. Theart, upon reasonable request https://stellenbosch.sharepoint.com/:f:/s/TheartLTS/EvwknpLzzUVJiVSa8bJ511oBOICi_dZaAWwNYxmL-jO6_Q?email=rptheart%40sun.ac.za&e=3MtfLZ.

Notes

1. https://github.com/David-Biggs/LDTS.

2. https://datatorch.io.

Additional information

Funding

This work was privately funded.