Multimodal object detection via probabilistic ensembling

YT Chen, J Shi, Z Ye, C Mertz, D Ramanan… - European Conference on …, 2022‏ - Springer
Object detection with multimodal inputs can improve many safety-critical systems such as
autonomous vehicles (AVs). Motivated by AVs that operate in both day and night, we study …

[PDF][PDF] Filtered channel features for pedestrian detection.

S Zhang, R Benenson, B Schiele - CVPR, 2015‏ - cv-foundation.org
This paper starts from the observation that multiple top performing pedestrian detectors can
be modelled by using an intermediate layer filtering low-level features in combination with a …

Semantic channels for fast pedestrian detection

AD Costea, S Nedevschi - Proceedings of the IEEE …, 2016‏ - openaccess.thecvf.com
Pedestrian detection and semantic segmentation are high potential tasks for many real-time
applications. However most of the top performing approaches provide state of art results at …

[HTML][HTML] Evidential query-by-committee active learning for pedestrian detection in high-density crowds

J Vandoni, E Aldea, S Le Hégarat-Mascle - International Journal of …, 2019‏ - Elsevier
The automatic detection of pedestrians in dense crowds has become recently a very active
topic of research due to the implications for public safety, and also due to the increased …

Fast multiple objects detection and tracking fusing color camera and 3D LIDAR for intelligent vehicles

S Hwang, N Kim, Y Choi, S Lee… - 2016 13th international …, 2016‏ - ieeexplore.ieee.org
For many robotics and intelligent vehicle applications, detection and tracking multiple
objects (DATMO) is one of the most important components. However, most of the DATMO …

Misaligned RGB-Infrared Object Detection via Adaptive Dual-Discrepancy Calibration

M He, Q Wu, KN Ngan, F Jiang, F Meng, L Xu - Remote Sensing, 2023‏ - mdpi.com
Object detection based on RGB and infrared images has emerged as a crucial research
area in computer vision, and the synergy of RGB-Infrared ensures the robustness of object …

[HTML][HTML] Face pixel detection using evidential calibration and fusion

P Minary, F Pichon, D Mercier, E Lefevre… - International Journal of …, 2017‏ - Elsevier
Due to legal reasons, faces on a given image may have to be blurred. This may be achieved
by combining several information sources, which may provide information at different levels …

Using the conflict in Dempster–Shafer evidence theory as a rejection criterion in classifier output combination for 3D human action recognition

A Perez, H Tabia, D Declercq, A Zanotti - Image and Vision Computing, 2016‏ - Elsevier
In this paper, we propose a comprehensive solution to 3D human action recognition
including feature extraction, classification, and multiple classifier combination. We effectively …

Looking at pedestrians at different scales: A multiresolution approach and evaluations

RN Rajaram, E Ohn-Bar… - IEEE Transactions on …, 2016‏ - ieeexplore.ieee.org
Typically, in a detector framework, the model size is fixed at the size of the smallest object to
be detected, and larger objects are detected by scaling the input image. The information lost …

Detect2rank: Combining object detectors using learning to rank

S Karaoglu, Y Liu, T Gevers - IEEE Transactions on Image …, 2015‏ - ieeexplore.ieee.org
Object detection is an important research area in the field of computer vision. Many detection
algorithms have been proposed. However, each object detector relies on specific …