Bottom-up and Layerwise Domain Adaptation for Pedestrian Detection in Thermal Images
نویسندگان
چکیده
Pedestrian detection is a canonical problem for safety and security applications, it remains challenging due to the highly variable lighting conditions in which pedestrians must be detected. This article investigates several domain adaptation approaches adapt RGB-trained detectors thermal domain. Building on our earlier work privacy-preserving pedestrian detection, we conducted an extensive experimental evaluation comparing top-down bottom-up also propose two new strategies. For adaptation, leverage detector pre-trained RGB imagery efficiently perform Our include steps: first, training adapter segment corresponding initial layers of adapts input distribution; then, reconnect original final with loss. To best knowledge, outperform best-performing single-modality results KAIST state art FLIR.
منابع مشابه
Unsupervised Deep Domain Adaptation for Pedestrian Detection
This paper addresses the problem of unsupervised domain adaptation on the task of pedestrian detection in crowded scenes. First, we utilize an iterative algorithm to iteratively select and auto-annotate positive pedestrian samples with high confidence as the training samples for the target domain. Meanwhile, we also reuse negative samples from the source domain to compensate for the imbalance b...
متن کاملDomain Adaptation for Pedestrian Detection Based on Prediction Consistency
Pedestrian detection is an active area of research in computer vision. It remains a quite challenging problem in many applications where many factors cause a mismatch between source dataset used to train the pedestrian detector and samples in the target scene. In this paper, we propose a novel domain adaptation model for merging plentiful source domain samples with scared target domain samples ...
متن کاملPedestrian Detection in Infrared Images
This paper describes an approach for pedestrian detection in infrared images. The developed system has been implemented on an experimental vehicle equipped with an infrared camera and preliminarily tested in different situations. It is based on the localization of warm symmetrical objects with specific size and aspect ratio; since also road infrastructures and other road participants may have s...
متن کاملSample-oriented Domain Adaptation for Image Classification
Image processing is a method to perform some operations on an image, in order to get an enhanced image or to extract some useful information from it. The conventional image processing algorithms cannot perform well in scenarios where the training images (source domain) that are used to learn the model have a different distribution with test images (target domain). Also, many real world applicat...
متن کاملShape-based Pedestrian Detection in Infrared Images
With the increase of requirement for improving the safety of night driving, automatic pedestrian detection has received more and more attraction. This paper mainly introduces a pedestrian detection method in infrared images. Base on the properties of infrared images, we present a two-step pedestrian detection method including pedestrian candidate selection and validation. The first step is loca...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: ACM Transactions on Multimedia Computing, Communications, and Applications
سال: 2021
ISSN: ['1551-6857', '1551-6865']
DOI: https://doi.org/10.1145/3418213