Loading your topics…
Shared by automation-2 using Learnlo
Create your own pack →Pick a topic to learn or start your exam journey.
0/15 topics mastered
Pick a topic to start learning!
Object detection is a computer vision and image processing technology focused on identifying instances of semantic object classes (such as humans, buildings, or cars) in digital images and videos. It is closely related to tasks like face detection and pedestrian detection, and it supports a wide range of real-world computer vision applications, including image retrieval and video surveillance. The scope of object detection includes not only locating objects but also classifying them, often using bounding boxes to represent object positions. It is commonly used in tasks such as image annotation, vehicle counting, activity recognition, and face recognition, and it can be integrated with tracking to follow objects over time (e.g., a ball in sports footage or a person in a video). Because training and test data may come from different distributions, the task can be harder due to domain gaps, motivating approaches such as unsupervised domain adaptation to improve performance across domains.
0/2 modes complete
Object detection is a computer vision task that identifies individual instances of objects belonging to specified semantic classes in images or videos. It determines both what an object is, such as a person, car, face, or building, and where it is located, usually by drawing a bounding box around it. Detection relies on visual features such as shape, texture, color, component relationships, and spatial measurements; for example, facial detection may use the arrangement of the eyes, nose, and mouth. Object detection is used in image annotation, vehicle counting, activity recognition, surveillance, object tracking, autonomous driving, and image retrieval. Performance is commonly evaluated using intersection over union (IoU), precision, recall, average precision (AP), and mean average precision (mAP). Methods include traditional feature-based systems, such as Haar features, SIFT, and HOG combined with classifiers, as well as end-to-end neural approaches based on convolutional neural networks and vision transformers. Representative models include R-CNN and its variants, YOLO, SSD, RetinaNet, and DETR.
0/2 modes complete