Town Square Activity Detection Dataset

Dataset Description This repository contains a dataset of object detection and instance segmentation events recorded over a 538-day period, from October 26, 2023 to April 16, 2025. The dataset comprises individual records, capturing temporal, spatial, and classification data for objects identified in an open access video broadcast from the town of Sant Mateu, Spain. Dataset Structure The repository contains a series of CSV files [*] (e.g., detections_01.csv, detections_02.csv, etc.). These files collectively serve as the primary dataset. They are partitioned for ease of handling but share an identical schema. Each record encapsulates granular detection events, including the temporal timestamp, categorical class ID, model confidence metric, and spatial geometry. Comprehensive details regarding the columns found in all files are provided in the section below. [*] 2025-11-30, The files have been updated to correct structural problems. Dataset Codebook All CSV files in this repository follow the same 8-column structure: Column Name Data Type Description time String Timestamp of the detection in YYYY-MM-DD HH:MM:SSformat. class_id Integer Integer representing the object category based on the COCO dataset. Detected classes include: Class 0 (person), Class 1 (bicycle), Class 2 (car), Class 3 (motorcycle), Class 5 (bus), and Class 7 (truck). confidence Float Model certainty score (0.0 - 1.0). xmin Float X-coordinate of the bounding box's top-left corner (pixels). ymin Float Y-coordinate of the bounding box's top-left corner (pixels). xmax Float X-coordinate of the bounding box's bottom-right corner (pixels). ymax Float Y-coordinate of the bounding box's bottom-right corner (pixels). segment_mask String Contains a stringified list of [x, y] pixel coordinates that form a closed polygon around the detected object.