# Object and Boundary Detection in Images

> Object detection engineering across one- and two-stage detectors, IoU, NMS, boundary extraction and end-to-end latency.

- Author: Muhammet Ali Köker
- Language: en
- Canonical: https://alikoker.com.tr/en/object-and-boundary-detection-in-images
- Translation: https://alikoker.com.tr/goruntude-nesne-tanima
- Published: 2021-10-27T19:17:36+03:00
- Modified: 2026-08-31T22:21:00+03:00
- Verified: 2026-08-31T22:07:00+03:00
- Type: article

Object detection identifies both what objects are present and where they are located. Depending on the application, outputs may be bounding boxes, contours or masks.

## Detector families

Two-stage detectors first generate candidate regions and then classify and refine them. One-stage methods such as [YOLO](/en/wiki/yolo) predict class and location in a single pass and are widely used in low-latency applications.

Small objects, dense scenes and high input resolution change the trade-off between computation and accuracy.

## Overlap and post-processing

IoU measures overlap between predicted and reference boxes. When many candidates correspond to the same object, [Non-Maximum Suppression](/en/wiki/non-maximum-suppression) removes duplicates according to confidence and overlap thresholds.

Boundary extraction can use gradient-based techniques such as Canny, active contours or instance-segmentation models.

## Real-time performance

FPS alone does not describe end-to-end latency. Decode, resize, memory transfers, model execution, NMS and serialisation all contribute to total delay.

Throughput and single-frame latency should be measured separately, with target hardware and the surrounding data path treated as part of the detector system.

## Cite This Work

Köker, M. A. (2021). Object and Boundary Detection in Images. alikoker.com.tr. https://alikoker.com.tr/en/object-and-boundary-detection-in-images

- BibTeX: https://alikoker.com.tr/en/object-and-boundary-detection-in-images.bib
- RIS: https://alikoker.com.tr/en/object-and-boundary-detection-in-images.ris
- CSL-JSON: https://alikoker.com.tr/en/object-and-boundary-detection-in-images.csl.json