Object detection
Object detection is a computer-vision task that identifies object instances in visual data, assigns them categories, and estimates their locations.
Machine Learning Platform Engineering
Object detection is a computer-vision task that identifies objects in an image or other visual input and locates them with bounding regions.
- How it is used
- Uses ID card detection to connect data preparation, reproducible pipelines, and monitoring in a production ML workflow.
- How deep it goes
- Works through dataset layout, pipeline components, and image-drift checks, but does not detail detector architecture or bounding-region prediction.
- Examples
- Uses an ID card dataset, a single-class YOLOv8 configuration, a 75/15/10 split, and deliberately darkened images for drift checking.
- What you can do after
- Operate/configure it by preparing YOLOv8 data with Kubeflow Pipelines and checking image-property drift with deepchecks.
Read how Machine Learning Platform Engineering explains object detection →
Inside Deep Learning: Math, Algorithms, Models
A vision task in which a system identifies and localizes multiple objects in a single image, often producing several predictions per image.
- How it is used
- Handles images that may be empty or contain multiple objects requiring both category labels and locations.
- How deep it goes
- Descends from task definition to segmentation, bounding boxes, Faster R-CNN components, target formats, batching, training, and inference.
- Examples
- Uses birds, horses, people, cars, stop signs, and synthetic MNIST digits to illustrate detection targets and predictions.
- What you can do after
- Build it from scratch with PyTorch data targets, custom collation, Faster R-CNN training, inference, and plotted predictions.
Read how Inside Deep Learning: Math, Algorithms, Models explains object detection →
Hugging Face in Action
Object detection is the machine learning task of identifying and locating objects within images or video.
- How it is used
- Applies pretrained Hugging Face models to identify and locate objects in images or video.
- How deep it goes
- Explains labels, probabilities, bounding boxes, browser inference, and Python execution without deriving detection internals.
- Examples
- Demonstrates office-image detection, a dog-and-cat image, confidence scores, and plotted bounding boxes.
- What you can do after
- Apply it via the Hosted Inference API or Transformers to return labels, scores, and bounding boxes.
Designing Deep Learning Systems: A guide for software engineers
Object detection is the computer-vision task of locating instances of target object classes in images and assigning labels to them.
- How it is used
- Organizes image collection, bounding-box labeling, dataset versioning, and model training into an automated production workflow.
- How deep it goes
- Explains the labeling and training pipeline operationally, but does not detail detection-model architecture or inference algorithms.
- Examples
- Uses raw and labeled image datasets, a labeling UI, generated label files, training containers, and saved model files.
- What you can do after
- Build an automated training workflow that retrains models when newly labeled images enter the versioned dataset.
Read how Designing Deep Learning Systems: A guide for software engineers explains object detection →
Math and Architectures of Deep Learning
A computer-vision task of identifying object categories in an image and estimating their spatial locations, often with bounding boxes.
- How it is used
- Frames computer vision as simultaneous object categorization and spatial localization.
- How deep it goes
- Defines bounding-box coordinates and sketches R-CNN region classification, without detailing detector training or later architectures.
- Examples
- Uses images containing a bird, plane, Superman, and four stacked animals to illustrate recognition and localization.
- What you can do after
- Evaluate/understand how detectors extend image classification by assigning categories and bounding boxes to objects.
Read how Math and Architectures of Deep Learning explains object detection →
Related concepts
- image segmentationcontrasts with · Image segmentation is a computer-vision task that partitions an image and assigns labels to its pixels or regions to delineate objects or meaningful areas.
- computer visionpart of · Computer vision is the field of computing concerned with using computational methods to extract and interpret information from images, video, and other visual data.
- bounding boxproduces · A bounding box is an axis-aligned rectangular or hyperrectangular region defined by coordinate limits that encloses or localizes an object, area, or set of points.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.