computer vision | Ag Data Commons

CameraTrapDetectoR Pig Model

This dataset contains the model weights, architecture, and class label dictionary for CameraTrapDetectoR pig-only model version 1. The model architecture is a FasterRCNN object detection model with a ResNet50 backbone. This model identifies and counts wild pigs in camera trap images. It also includes categories for non-pig detections (animal, human, or vehicle), and a background class.

CameraTrapDetectoR General Model

This dataset contains the model weights, architecture, and class label dictionary for CameraTrapDetectoR general model version 1. The model architecture is a FasterRCNN object detection model with a ResNet50 backbone. This model identifies and counts mammals and birds in camera trap images, and includes categories for humans, vehicles, and a background class.

CameraTrapDetectoR Family Model

This dataset contains the model weights, architecture, and class label dictionary for CameraTrapDetectoR family model version 1. The model architecture is a FasterRCNN object detection model with a ResNet50 backbone. This model identifies and counts animals from 33 North American taxonomic families in camera trap images, including humans vehicles and a background class.

CameraTrapDetectoR Species Model

CameraTrapDetectoR is an R package that uses deep learning computer vision models to automatically detect, count, and classify common North American domestic and wild species in camera trap images. Data for all versions of the taxonomic species model are located in this dataset. This dataset contains model weights, architectures, and class label dictionaries for the CameraTrapDetectoR species models.

2x zip

SNAPMe: A Benchmark Dataset of Food Photos with Food Records for Evaluation of Computer Vision Algorithms in the Context of Dietary Assessment

We conducted the Surveying Nutrient Assessment with Photographs of Meals (SNAPMe) Study (ClinicalTrials ID: NCT05008653) to develop a benchmark dataset of food photographs paired with traditional food records. The SNAPMe DB includes 1,475 “before” photos of non-packaged foods, 1,436 “after” photos of non-packaged foods, 203 “front” photos of packaged foods, and 196 “ingredient” labels of packaged foods. Each line item of each ASA24 food record is linked to the relevant photo. These data will be transformative for the improvement of artificial intelligence algorithms for the adoption of photo-based dietary assessment in nutrition research.

Data from: Efficient imaging and computer vision detection of two cell shapes in young cotton fibers

Data presented show the AI-assisted visualization of multiple cotton fiber tips in one image. Cotton fiber sample preparation, digital image collection, and image analysis are described, including test images, training/validation sets, and annotations.

10x zip
2x json

X-ray CT data with semantic annotations for the paper "A workflow for segmenting soil and plant X-ray CT images with deep learning in Google’s Colaboratory"

Annotated x-ray ct data from walnut leaves (J. regia), an almond bud (P. Dulcis), and a soil aggregate for training deep learning models to segment and extract data from images using code found at: https://github.com/daripp/XCT_FCN

3x zip

Data from: Solving the Robot-World Hand-Eye(s) Calibration Problem with Iterative Methods

These datasets were generated for calibrating robot-camera systems and to develop and test new robot-world, hand-eye calibration methods.

txt
9x zip

Code from: Using cameras for precise measurement of two-dimensional plant features

Images are used frequently in plant phenotyping to capture measurements. This chapter offers a repeatable method for capturing two-dimensional measurements of plant parts in field or laboratory settings using a variety of camera styles (cellular phone, DSLR), with the addition of a printed calibration pattern. The method is based on calibrating the camera using information available from the EXIF tags from the image, as well as visual information from the pattern. Code is provided to implement the method, as well as a dataset for testing. We include steps to verify protocol correctness by imaging an artifact. The use of this protocol for two-dimensional plant phenotypoing will allow data capture from different cameras and environments, with comparison on the same physical scale.

html

Data from: Apple flower detection using deep convolutional networks

With the goal of automating bloom intensity estimation, a method a novel method for apple flower detection is presented in which a pre-trained convolutional neural network (CNN) is fine-tuned to become specially sensitive to flowers.

6x mp4