Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
118
datasets available to search
ShareScore release 0.7.1
Dataset results
118 results for “object detection”
Strawberry dataset for object detection
<p>Object detection dataset with annotated ripe and unripe strawberries and their peduncles. Data is annotated in YOLO format. Collected for: ”Real-Time CNN-based Computer Vision System for Open-Field Strawberry Harvesting Robot” <a href="https://doi.org/10.1016/j.ifacol.2022.11.109">https://doi.org/10.1016/j.ifacol.2022.11.109</a> .</p>
Animal Recognition Using Methods Of Fine-Grained Visual Analysis - YOLOv5 Object Detection Dataset (Oxford-IIIT Pet)
<p>Preprocessed dataset for Oxford-IIIT Pet in YOLOv5 format.. Ground truth labels for head bounding boxes, body bounding boxes (derived from segmentation mask).</p>
Animal Recognition Using Methods Of Fine-Grained Visual Analysis - YOLOv5 Object Detection Dataset (Tsinghua Dogs)
<p>Preprocessed dataset for Tsinghua Dogs in YOLOv5 format.. Ground truth labels for head bounding boxes, body bounding boxes</p>
Common guillemots in the Baltic Sea studied with video surveillance and object detection: raw data, annotations, model, and model outputs
<p>The data comes from common guillemots studied at Stora Karlsö, Sweden between 2019 and 2021. The common guillemots breed at an artificial cliff, and has been filmed continusly from above over three breeding seasons. Using the video material, a YOLOv5 model has been trained to detect adult birds, chicks and eggs. The dataset contains annotations (bounding boxes) used for training the model, the model itself, and outputs from the model (object detections).</p> <p>The data can be used and shared freely.</p>
Canola seedling object detection dataset
<div> <div>This is a single-class object detection dataset containing aerial images of early-season canola fields. The objects of interest are canola seedlings. The images were acquired by a Hasselblad L1D-20c camera mounted on a DJI Mavic 2 Pro Drone, which was flown at a height of 2 metres. The dataset contains 431 images and 77059 canola seedling bounding box annotations.</div> </div>
An Objective Detection of Separation Scenario in Tropical Cyclone Trajectories Based on Ensemble Weather Forecast Data
<p>This repository contains the data used in "An Objective Detection of Separation Scenario in Tropical Cyclone Trajectories Based on Ensemble Weather Forecast Data" by Oettli and Kotsuki (submitted to Journal of Geophysical Research: Atmospheres).</p>
The Potential of Deep Learning Object Detection in Citizen-Driven Snail Host Monitoring to Map Putative Disease Transmission Sites
<p><a name="_Hlk158802145"></a><span>Schistosomiasis is a neglected tropical disease caused by parasitic flukes transmitted by freshwater snails. Despite increasing efforts of mass drug administration, schistosomiasis remains a public health concern and the World Health Organization recommends complementary snail control. To address the need of broad-scale and actual snail distribution data to guide snail control, we adopted a citizen science approach and recruited citizen scientists (CS) to perform weekly snail sampling in the endemic setting in Uganda. Snails were identified, sorted and counted according to genus, photographed and uploaded for expert-led validation and feedback. However, expert validation is time-consuming and introduces a delay in verified data output. Thus, artificial intelligence could provide a solution by means of automated detection and counting of multiple snails collected from the field. Trained on approximately 2500 citizen-collected images, the resulting model can simultaneously detect and count Biomphalaria and Radix snails with average precision of 98.1% and 98.8% respectively. The object detection model also agreed with the expert’s decision averagely for 98.8% of the test images and could be ran in real-time (24.6 images per second). We conclude that the automatic and instant detection can rapidly and reliably validate data submitted by CS in the field, ultimately minimizing the expert validation efforts and thereby facilitating the mapping of putative schistosomiasis transmission sites. An extension to a mobile application could equip citizen scientists in remote areas with instant learning opportunities and expert-like identification skills, overcoming the need for on-site training and extensive expert intervention. </span></p>
Figure 8. F1 scores for YOLOv5 in Use of open-source object detection algorithms to detect Palmer amaranth (Amoronthus polmeri) in soybean
Figure 8. F1 scores for YOLOv5 indicating the harmonic mean between precision and recall scores. Data indicated that detection results for both species would be best at a confidence threshold of 0.298.
Figure 11. YOLOv5 in Use of open-source object detection algorithms to detect Palmer amaranth (Amoronthus polmeri) in soybean
Figure 11. YOLOv5 precision (A), recall (B), and F1 score (C) changes as a function of Amoronthus polmeri density (plants m−2).
Figure 10. Detection results for YOLOv5 with a in Use of open-source object detection algorithms to detect Palmer amaranth (Amoronthus polmeri) in soybean
Figure 10. Detection results for YOLOv5 with a confidence interval of 0.15. False-positive detections of Mollugo verticillata and Abutilon theophrasti as Amoronthus polmeri are denoted by arrows pointing from "A" and "B," respectively.
Figure 9. YOLOv5 in Use of open-source object detection algorithms to detect Palmer amaranth (Amoronthus polmeri) in soybean
Figure 9. YOLOv5 detection results for Amoronthus polmeri and soybean using confidence thresholds of 0.15 (A) and 0.70 (B). The likelihood of false-negative (FN) detections increases as confidence thresholds increase, as can be seen in B. Objects assigned a confidence interval of less than 0.70 are not detected in B. FN A. palmeri and soybean detections in B are indicated by the orange and white arrows, respectively.
Figure 7 in Use of open-source object detection algorithms to detect Palmer amaranth (Amoronthus polmeri) in soybean
Figure 7. Image annotation of soybean at the R2 growth stage. As soybean populations were much higher than Amoronthus polmeri populations, there was a high level of soybean overlap. Therefore, it was necessary to include multiple soybean plants in each image. However, A. polmeri plants typically did not have as much overlap, and in most cases, it was much easier to identify and label individual plants.
Figure 3 in Use of open-source object detection algorithms to detect Palmer amaranth (Amoronthus polmeri) in soybean
Figure 3. Intersection over union (IoU) equation, defined as the overlap between the ground truth annotation and the computer prediction bounding box, divided by the total area of the two bounding boxes.IoU overlaps greater than 0.5 were considered true-positive predictions,whereas overlaps less than 0.5 were considered false-positive predictions.
Figure 2 in Use of open-source object detection algorithms to detect Palmer amaranth (Amoronthus polmeri) in soybean
Figure 2. Illustration of the annotation process. Amoronthus polmeri and soybean plants are labeled in this figure with orange and white boxes, respectively. Bounding boxes overlap with neighboring bounding boxes when plant features are irregular. In cases where a single bounding box could not encompass a plant without including a plant of another species, multiple irregular bounding boxes were drawn on a single specimen.
Figure 4 in Use of open-source object detection algorithms to detect Palmer amaranth (Amoronthus polmeri) in soybean
Figure 4. Mean average precision (mAP) results of each model after training. YOLOv5 was considered the best-performing algorithm of each tested model with a mAP of 0.77.
Figure 6. Precision–recall curve for YOLOv5. Amoronthus polmeri achieved a in Use of open-source object detection algorithms to detect Palmer amaranth (Amoronthus polmeri) in soybean
Figure 6. Precision–recall curve for YOLOv5. Amoronthus polmeri achieved a slightly higher average precision (AP) (0.788) than soybean. Solid blue line represents mean average precision (mAP) computed on the test data set. The AP for each class and the mAP for the overall algorithm were representative of the area of the graph under each respective curve.
Figure 5 in Use of open-source object detection algorithms to detect Palmer amaranth (Amoronthus polmeri) in soybean
Figure 5. Change in mean average precision (mAP) @ 0.5 over each epoch during training. mAP was reported after the completion of each epoch. Training was terminated after visual inspection of curve and when mAP @ 0.5 curve was seen to "plateau."
Transfer learning with generative models for object detection on limited datasets
<p>The provided datasets are used for the analysis in the work "Transfer learning with generative models for object detection on limited datasets" (https://doi.org/10.1088/2632-2153/ad65b5). The availability of data is limited in some fields, especially for object detection tasks, where it is necessary to have correctly labeled bounding boxes around each object. A notable example of such data scarcity is found in the domain of marine biology, where it is useful to develop methods to automatically detect submarine species for environmental monitoring. To address this data limitation, the state-of-the-art machine learning strategies employ two main approaches. The first involves pretraining models on existing datasets before generalizing to the specific domain of interest. The second strategy is to create synthetic datasets specifically tailored to the target domain using methods like copy-paste techniques or ad-hoc simulators. The first strategy often faces a significant domain shift, while the second demands custom solutions crafted for the specific task. In response to these challenges, here we propose a transfer learning framework that is valid for a generic scenario. In this framework, generated images help to improve the performances of an object detector in a few-real data regime. This is achieved through a diffusion-based generative model that was pretrained on large generic datasets. With respect to the state-of-the-art, we find that it is not necessary to fine tune the generative model on the specific domain of interest. We believe that this is an important advance because it mitigates the labor-intensive task of manual labeling the images in object detection tasks. We validate our approach focusing on fishes in an underwater environment, and on the more common domain of cars in an urban setting. Our method achieves detection performance comparable to models trained on thousands of images, using only a few hundreds of input data. Our results pave the way for new generative AI-based protocols for machine learning applications in various domains, for instance ranging from geophysics to biology and medicine. The provided datasets are built with the help of Gligen and the already existing NuImages, Ozfish and Deepfish datasets. The file "CarGenerated.zip" contains images generated with Gligen and with provided bounding boxes around cars in an urban environment. The file "fishes_on_bkg.zip" provides fish images generated with fishes from Deepfish inpainted with Gligen on generated backgrounds. The file "fish_text.zip" contains images completely generated with Gligen containing fishes with annotated bounding boxes. Finally, the file "oz_masked_512.zip" contains a simpler dataset of copy paste images of Deepfish fishes on Ozfish backrounds. All the files contains the images saved in different folders for training and validation, plus an index file called gt_fish.csv for the bounding boxes.</p>
ODDS: Real-Time Object Detection using Depth Sensors on Embedded GPUs
<p> ODDS Smart Building Depth Dataset</p> <p>#Introduction:</p> <p>The goal of this dataset is to facilitate research focusing on recognizing objects in smart buildings using the depth sensor mounted at the ceiling. This dataset contains annotations of depth images for eight frequently seen object classes. The classes are: person, backpack, laptop, gun, phone, umbrella, cup, and box.</p> <p><br> #Data Collection:</p> <p>We collected data from two settings. We had Kinect mounted at a 9.3 feet ceiling near to a 6 feet wide door. We also used a tripod with a horizontal extender holding the kinect at a similar height looking downwards. We asked about 20 volunteers to enter and exit a number of times each in different directions (3 times walking straight, 3 times walking towards left side, 3 times walking towards right side) holding objects in many different ways and poses underneath the Kinect. Each subject was using his/her own backpack, purse, laptop, etc. As a result, we considered varieties within the same object, e.g., for laptops, we considered Macbooks, HP laptops, Lenovo laptops of different years and models, and for backpacks, we considered backpacks, side bags, and purse of women. We asked the subjects to walk while holding it in many ways, e.g., for laptop, the laptop was fully open, partially closed, and fully closed while carried. Also, people hold laptops in front and side of their bodies, and underneath their elbow. The subjects carried their backpacks in their back, in their side at different levels from foot to shoulder. We wanted to collect data with real guns. However, bringing real guns to the office is prohibited. So, we obtained a few nerf guns and the subjects were carrying these guns pointing it to front, side, up, and down while walking.</p> <p><br> #Annotated Data Description:</p> <p>The Annotated dataset is created following the structure of Pascal VOC devkit, so that the data preparation becomes simple and it can be used quickly with different with object detection libraries that are friendly to Pascal VOC style annotations (e.g. Faster-RCNN, YOLO, SSD). The annotated data consists of a set of images; each image has an annotation file giving a bounding box and object class label for each object in one of the eight classes present in the image. Multiple objects from multiple classes may be present in the same image. The dataset has 3 main directories:</p> <p>1)DepthImages: Contains all the images of training set and validation set. </p> <p>2)Annotations: Contains one xml file per image file, (e.g., 1.xml for image file 1.png). The xml file includes the bounding box annotations for all objects in the corresponding image. </p> <p>3)ImagesSets: Contains two text files training_samples.txt and testing_samples.txt. The training_samples.txt file has the name of images used in training and the testing_samples.txt has the name of images used for testing. (We randomly choose 80%, 20% split)</p> <p><br> #UnAnnotated Data Description:</p> <p>The un-annotated data consists of several set of depth images. No ground-truth annotation is available for these images yet. These un-annotated sets contain several challenging scenarios and no data has been collected from this office during annotated dataset construction. Hence, it will provide a way to test generalization performance of the algorithm.</p> <p><br> #Citation:</p> <p>If you use ODDS Smart Building dataset in your work, please cite the following reference in any publications:<br> @inproceedings{mithun2018odds,<br> title={ODDS: Real-Time Object Detection using Depth Sensors on Embedded GPUs},<br> author={Niluthpol Chowdhury Mithun and Sirajum Munir and Karen Guo and Charles Shelton},<br> booktitle={ ACM/IEEE Conference on Information Processing in Sensor Networks (IPSN)},<br> year={2018},<br> }<br> </p>
Logistics Transport Label Data - 'Lean Training Data Generation for Planar Object Detection Models in Unsteady Logistics Contexts'
<p>Example dataset described in ICMLA2019 Paper 'Lean Training Data Generation for Planar Object Detection Models in Unsteady Logistics Contexts' (Dörr, Brandt, Meyer, Pouls).</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.