Dataset Information

Labeled dataset for bee detection and direction estimation on entrance to beehive.

ABSTRACT: The datasets for bee detection, pose estimation and segmentation consist of organized folders containing both images and corresponding labels. The detection dataset comprises a total of 7200 individual frames collected at 8 different beehives. The pose dataset contains 400 images of bees annotated with two key points per bee. The first point marks a head, second point marks a stinger. All frames have a resolution of 1920×1080 pixels. The segmentation dataset contains 2300 cropped images of bees. These cropped images are annotated with triangular markers that aid in estimating directional vectors. The labels in all proposed datasets were saved in YOLO format. The labeling process was automated by training YOLOv8 model on a set of manually annotated images for bee detection. After detection, all the labels were visually revised and corrected. Frames were captured using stationary mounted camera 30 cm above beehive landing boards. The data collection period spanned from June to July 2023 in Vilnius district.

SUBMITTER: Sledevic T

PROVIDER: S-EPMC10831503 | biostudies-literature | 2024 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Labeled dataset for bee detection and direction estimation on entrance to beehive.

Sledevič Tomyslav T Matuzevičius Dalius D

Data in brief 20240111

The datasets for bee detection, pose estimation and segmentation consist of organized folders containing both images and corresponding labels. The detection dataset comprises a total of 7200 individual frames collected at 8 different beehives. The pose dataset contains 400 images of bees annotated with two key points per bee. The first point marks a head, second point marks a stinger. All frames have a resolution of 1920×1080 pixels. The segmentation dataset contains 2300 cropped images of bees. ...[more]

PMID: 38304387

Similar Datasets

Project description:The honey bee is the most essential pollinator and a key contributor to the natural ecosystem. There are numerous ways for thousands of bees in a hive to communicate with one another. Individual trajectories and social interactions are thus complex behavioral features that can provide valuable information for an ecological study. To study honey bee behavior, the key challenges that have resulted from unreliable studies include complexity (high density of similar objects, small objects, and occlusion), the variety of background scenes, the dynamism of individual bee movements, and the similarity between the bee body and the background in the beehive. This study investigated the tracking of individual bees in a beehive environment using a deep learning approach and a Kalman filter. Detection of multiple bees and individual object segmentation were performed using Mask R-CNN with a ResNet-101 backbone network. Subsequently, the Kalman filter was employed for tracking multiple bees by tracking the body of each bee across a sequence of image frames. Three metrics were used to assess the proposed framework: mean average precision (mAP) for multiple-object detection and segmentation tasks, CLEAR MOT for multiple object tracking tasks, and MOTS for multiple object tracking and segmentation tasks. For CLEAR MOT and MOTS metrics, accuracy (MOTA and MOTSA) and precision (MOTP and MOTSP) are considered. By employing videos from a custom-designed observation beehive, recorded at a frame rate of 30 frames per second (fps) and utilizing a continuous frame rate of 10 fps as input data, our system displayed impressive performance. It yielded satisfactory outcomes for tasks involving segmentation and tracking of multiple instances of bee behavior. For the multiple-object segmentation task based on Mask R-CNN, we achieved a 0.85 mAP. For the multiple-object-tracking task with the Kalman filter, we achieved 77.48% MOTA, 79.79% MOTSP, and 79.56% recall. For the overall system for multiple-object tracking and segmentation tasks, we achieved 77.00% MOTSA, 75.60% MOTSP, and 80.30% recall.

Project description:BACKGROUND: The impact of social parasites on their hosts' fitness is a strong selective pressure that can lead to the evolution of adapted defence strategies. Guarding the nest to prevent the intrusion of parasites is a widespread response of host species. If absolute rejection of strangers provides the best protection against parasites, more fine-tuned strategies can prove more adaptive. Guarding is indeed costly and not all strangers constitute a real threat. That is particularly true for worker reproductive parasitism in social insects since only a fraction of non-nestmate visitors, the fertile ones, can readily engage in parasitic reproduction. Guards should thus be more restrictive towards fertile than sterile non-nestmate workers. We here tested this hypothesis by examining the reaction of nest-entrance guards towards nestmate and non-nestmate workers with varying fertility levels in the bumble bee Bombus terrestris. Because social recognition in social insects mainly relies on cuticular lipids (CLs), chemical analysis was also conducted to examine whether workers' CLs could convey the relevant information upon which guards could base their decision. We thus aimed to determine whether an adapted defensive strategy to worker reproductive parasitism has evolved in B. terrestris colonies. RESULTS: Chemical analysis revealed that the cuticular chemical profiles of workers encode information about both their colony membership and their current fertility, therefore providing potential recognition cues for a suitable adjustment of the guards' defensive decisions. We found that guards were similarly tolerant towards sterile non-nestmate workers than towards nestmate workers. However, as predicted, guards responded more aggressively towards fertile non-nestmates. CONCLUSION: Our results show that B. terrestris guards discriminate non-nestmates that differ in their reproductive potential and respond more strongly to the individuals that are a greatest threat for the colony. Cuticular hydrocarbons are the probable cues underlying the specific recognition of reproductive parasites, with the specific profile of highly fertile bees eliciting the agonistic response when combined with non-colony membership information. Our study therefore provides a first piece of empirical evidence supporting the hypothesis that an adapted defensive strategy against worker reproductive parasitism exists in B. terrestris colonies.

Dataset Information

Labeled dataset for bee detection and direction estimation on entrance to beehive.

Publications

Labeled dataset for bee detection and direction estimation on entrance to beehive.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets