# rafaelpadilla/object-detection-metrics

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/rafaelpadilla-object-detection-metrics).**

5,098 stars · 1,034 forks · Python · mit

## Links

- GitHub: https://github.com/rafaelpadilla/Object-Detection-Metrics
- awesome-repositories: https://awesome-repositories.com/repository/rafaelpadilla-object-detection-metrics.md

## Topics

`average-precision` `bounding-boxes` `mean-average-precision` `metrics` `object-detection` `pascal-voc` `precision-recall`

## Description

This project is an object detection evaluation library and benchmarking tool designed to calculate precision, recall, and average precision for computer vision models. It provides a suite of utilities for parsing bounding box coordinates from text files and calculating spatial overlap to determine detection accuracy.

The toolkit features a command line interface for comparing ground truth files against model predictions. It includes a precision-recall curve generator to visualize the relationship between precision and recall across different confidence thresholds and an intersection over union calculator to measure the overlap between predicted and actual bounding boxes.

The library covers a broad range of model evaluation capabilities, including spatial metrics for true positive determination, average precision calculation through curve interpolation, and the ability to overlay ground truth and detected bounding boxes onto images for visual verification.

## Tags

### Artificial Intelligence & ML

- [Intersection Over Union Calculators](https://awesome-repositories.com/f/artificial-intelligence-ml/intersection-over-union-calculators.md) — Calculates intersection over union to determine if a detection is a true positive. ([source](https://github.com/rafaelpadilla/Object-Detection-Metrics#readme))
- [Object Detection Evaluators](https://awesome-repositories.com/f/artificial-intelligence-ml/model-prediction-evaluation/object-detection-evaluators.md) — Measures the accuracy of computer vision models by comparing predicted bounding boxes against ground truth labels.
- [Intersection over Union Calculators](https://awesome-repositories.com/f/artificial-intelligence-ml/anchor-box-systems/ground-truth-assignment-algorithms/intersection-over-union-calculators.md) — Determines prediction correctness by calculating the area of overlap between ground truth and detection bounding boxes.
- [Average Precision Calculators](https://awesome-repositories.com/f/artificial-intelligence-ml/average-precision-calculators.md) — Provides calculation of average precision using curve interpolation and all available data points. ([source](https://github.com/rafaelpadilla/Object-Detection-Metrics/blob/master/README.md))
- [Bounding Box Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/bounding-box-detection.md) — Implements representations for identifying and locating objects within images using rectangular boundaries. ([source](https://github.com/rafaelpadilla/Object-Detection-Metrics/tree/master/samples/sample_1))
- [Computer Vision Benchmarks](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-benchmarks.md) — Provides a standardized evaluation suite for measuring the accuracy and generalization of object detection models.
- [Detection Accuracy Metrics](https://awesome-repositories.com/f/artificial-intelligence-ml/detection-accuracy-metrics.md) — Computes precision, recall, and average precision using ground truth data and configurable overlap thresholds. ([source](https://github.com/rafaelpadilla/Object-Detection-Metrics/tree/master/samples/sample_2))
- [Prediction Thresholds](https://awesome-repositories.com/f/artificial-intelligence-ml/face-detection/confidence-filtering/prediction-thresholds.md) — Implements logic to compare model confidence scores against thresholds to balance precision and recall.
- [2D Object Detection Evaluations](https://awesome-repositories.com/f/artificial-intelligence-ml/model-evaluation-metrics/3d-detection-evaluations/2d-object-detection-evaluations.md) — Provides a toolkit for calculating precision, recall, and average precision based on ground truth and bounding box detections.
- [Model Performance Analysis](https://awesome-repositories.com/f/artificial-intelligence-ml/model-performance-analysis.md) — Calculates precision and recall metrics to evaluate how well a detection algorithm identifies objects.
- [Model Prediction Evaluation](https://awesome-repositories.com/f/artificial-intelligence-ml/model-prediction-evaluation.md) — Determines the prediction rate by comparing model outputs against ground truth labels. ([source](https://github.com/rafaelpadilla/Object-Detection-Metrics#readme))
- [Precision-Recall Curve Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/precision-recall-curve-generators.md) — Generates precision-recall curves to visualize the trade-off between sensitivity and accuracy. ([source](https://github.com/rafaelpadilla/Object-Detection-Metrics/blob/master/README.md))
- [Precision-Recall Curve Interpolations](https://awesome-repositories.com/f/artificial-intelligence-ml/precision-recall-curve-interpolations.md) — Calculates average precision by sampling the precision-recall curve at fixed intervals or using all available data points.
- [Precision-Recall Visualizations](https://awesome-repositories.com/f/artificial-intelligence-ml/precision-recall-visualizations.md) — Generates curves and graphs to analyze the trade off between detection sensitivity and accuracy across classes.
- [Accuracy Calculators](https://awesome-repositories.com/f/artificial-intelligence-ml/prediction-visualization/accuracy-calculators.md) — Calculates the percentage of correct positive predictions and true positives among ground truth labels. ([source](https://github.com/rafaelpadilla/Object-Detection-Metrics/blob/master/README.md))
- [Intersection Over Union Calculators](https://awesome-repositories.com/f/artificial-intelligence-ml/prediction-visualization/accuracy-calculators/intersection-over-union-calculators.md) — Measures the overlap between predicted and actual bounding boxes to determine detection accuracy.
- [Bounding Box Representations](https://awesome-repositories.com/f/artificial-intelligence-ml/bounding-box-regression/bounding-box-representations.md) — Stores and manages bounding box coordinates and labels using standardized spatial conventions. ([source](https://github.com/rafaelpadilla/Object-Detection-Metrics/tree/master/samples/sample_1))
- [Bounding Box Parsers](https://awesome-repositories.com/f/artificial-intelligence-ml/bounding-box-regression/bounding-box-representations/bounding-box-parsers.md) — Provides a parser that converts absolute and relative coordinate data from text files into structured objects.
- [Bounding Box Visualizers](https://awesome-repositories.com/f/artificial-intelligence-ml/bounding-box-regression/bounding-box-representations/bounding-box-visualizers.md) — Overlays ground truth and detected bounding boxes onto images for spatial accuracy verification. ([source](https://github.com/rafaelpadilla/Object-Detection-Metrics/tree/master/samples/sample_1))
- [Bounding Box Validation Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/bounding-box-regression/bounding-box-representations/bounding-box-visualizers/bounding-box-validation-tools.md) — Verifies model predictions by calculating intersection over union and overlaying detections on original images.
- [Coordinate Converters](https://awesome-repositories.com/f/artificial-intelligence-ml/bounding-box-regression/bounding-box-representations/coordinate-converters.md) — Includes utilities for transforming bounding box coordinates between absolute and relative spatial representations. ([source](https://github.com/rafaelpadilla/Object-Detection-Metrics/tree/master/samples/sample_2))
- [Coordinate Normalization Utilities](https://awesome-repositories.com/f/artificial-intelligence-ml/coordinate-normalization-utilities.md) — Provides tools for mapping pixel-based screen locations to consistent relative coordinate systems.
- [Model Benchmarking Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/model-benchmarking-tools.md) — Ships a tool for comparing model performance across different datasets using standard object detection metrics.
- [Model Performance Evaluators](https://awesome-repositories.com/f/artificial-intelligence-ml/model-performance-evaluators.md) — Provides a command line interface to compare ground truth files against detection results for performance quantification. ([source](https://github.com/rafaelpadilla/Object-Detection-Metrics#readme))

### Data & Databases

- [Precision-Recall Curve Generators](https://awesome-repositories.com/f/data-databases/indexing-and-search/recall-optimization/precision-recall-curve-generators.md) — Plots and visualizes the relationship between precision and recall across various confidence thresholds.
- [Class-Specific Metric Aggregations](https://awesome-repositories.com/f/data-databases/real-time-data-aggregators/performance-metric-aggregators/class-specific-metric-aggregations.md) — Groups detection and ground truth data by category to compute independent performance scores for each class.
- [Text File Parsers](https://awesome-repositories.com/f/data-databases/text-file-parsers.md) — Provides tools for converting delimited text files containing coordinate data into structured objects.