Images

284 images

Explore Dataset

Yellow Sticky Traps Dataset

This dataset contains images of yellow sticky traps and bounding box annotations for three classes of flying insects found in greenhouses. The annotated classes are Macrolophus pygmaeus, Nesidiocoris tenuis and Trialeurodes vaporariorum (Whitefly).

The dataset is based on the original version "Raw data from Yellow Sticky Traps with insects for training of deep learning Convolutional Neural Network for object detection" by A.T. Nieuwenhuizen et. al. (see source). This version contains corrected annotations and uniform image orientations.

Details

The yellow sticky dataset consists of:

284 landscape JPEG images of 5184 x 3456 px
8114 bounding box annotations:
- 1619 Macrolophus pygmaeus
- 688 Nesidiocoris tenuis
- 5807 Trialeurodes vaporariorum (Whitefly)

Compared to the original dataset by A.T. Nieuwenhuizen et. al. the Exif image rotation information were fixed to match the landscape-oriented images.

Additionally, the annotation quality was improved by labeling previously unlabeled objects, fixing wrong labeled classes, resizing bounding boxes and improving the location of bounding boxes.

The annotations were improved with LabelImg, created by Tzutalin. Ground truth information is stored in XML files in PASCAL VOC format.

The labeling process was carried out to the best of our knowledge.

Cite This Project

If you use this dataset in a research paper, please cite it using the following BibTeX:

@misc{
                            yellow-sticky-traps-bwxut_dataset,
                            title = { Yellow Sticky Traps Dataset },
                            type = { Open Source Dataset },
                            author = { Project },
                            howpublished = { \url{ https://universe.roboflow.com/project-lrivq/yellow-sticky-traps-bwxut } },
                            url = { https://universe.roboflow.com/project-lrivq/yellow-sticky-traps-bwxut },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2022 },
                            month = { jun },
                            note = { visited on 2024-05-02 },
                            }