Lecture

Multi-Object Tracking and Person Re-Identification

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Description

This lecture covers Multi-Object Tracking (MOT) and Person Re-Identification (ReID). It starts with an overview of MOT, discussing the challenges and related tasks. The lecture then delves into the problem statement of MOT, distinguishing between online and offline tracking methods. It explains different tracking paradigms, focusing on Tracking-by-Detection as the most popular approach. The lecture also presents a simple online tracking-by-detection method, detailing the process of detection, association, and the Hungarian algorithm. Additionally, it explores the concept of Person Re-Identification, explaining the retrieval task and the metric learning aspect. The lecture concludes by discussing the state-of-the-art methods for online tracking-by-detection and the training process of a ReID model.

Official source

Related concepts (24)

Eye tracking

Eye tracking is the process of measuring either the point of gaze (where one is looking) or the motion of an eye relative to the head. An eye tracker is a device for measuring eye positions and eye movement. Eye trackers are used in research on the visual system, in psychology, in psycholinguistics, marketing, as an input device for human-computer interaction, and in product design. In addition, eye trackers are increasingly being used for assistive and rehabilitative applications such as controlling wheelchairs, robotic arms, and prostheses.

Object detection

Object detection is a computer technology related to computer vision and that deals with detecting instances of semantic objects of a certain class (such as humans, buildings, or cars) in digital images and videos. Well-researched domains of object detection include face detection and pedestrian detection. Object detection has applications in many areas of computer vision, including and video surveillance. It is widely used in computer vision tasks such as , vehicle counting, activity recognition, face detection, face recognition, video object co-segmentation.

Corner detection

Corner detection is an approach used within computer vision systems to extract certain kinds of features and infer the contents of an image. Corner detection is frequently used in motion detection, , video tracking, image mosaicing, panorama stitching, 3D reconstruction and object recognition. Corner detection overlaps with the topic of interest point detection. A corner can be defined as the intersection of two edges. A corner can also be defined as a point for which there are two dominant and different edge directions in a local neighbourhood of the point.

Finger tracking

In the field of gesture recognition and , finger tracking is a high-resolution technique developed in 1969 that is employed to know the consecutive position of the fingers of the user and hence represent objects in 3D. In addition to that, the finger tracking technique is used as a tool of the computer, acting as an external device in our computer, similar to a keyboard and a mouse. The finger tracking system is focused on user-data interaction, where the user interacts with virtual data, by handling through the fingers the volumetric of a 3D object that we want to represent.

Learning to rank

Learning to rank or machine-learned ranking (MLR) is the application of machine learning, typically supervised, semi-supervised or reinforcement learning, in the construction of ranking models for information retrieval systems. Training data consists of lists of items with some partial order specified between items in each list. This order is typically induced by giving a numerical or ordinal score or a binary judgment (e.g. "relevant" or "not relevant") for each item.

Related lectures (6)

Proper Feature Size: Image Analysis MOOC: Image Processing and Analysis for Life Scientists

Delves into choosing a proper feature size for image analysis in life sciences, presenting a Rule Of Thumb for defining object size in pixels.

Computer Vision Basics: Image Processing and Feature Detection

Covers the basics of computer vision, focusing on image processing techniques and feature detection.

Delineation: Techniques and Applications

Explores techniques for delineation, including Hough transform, gradient orientation, and shape detection, emphasizing the importance of combining graph-based techniques and machine learning.

Detecting Objects: Independent Channels MOOC: Image Processing and Analysis for Life Scientists

Emphasizes the need for independent channels when detecting objects in images.

Convolutional Neural Networks