CAMEL Dataset for Visual and Thermal Infrared Multiple Object Detection and Tracking

Gebhardt, Evan; Wolf, Marilyn

doi:10.1109/avss.2018.8639094

Cited by 46 publications

(11 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dropout was added to the output of the backbone with a 0.2 probability of dropping. Evaluation was performed on the CAMEL dataset [13] which contains registered RGB-IR pairs at a resolution of 256 × 336 and 5 classes of objects annotated. The test set contains six sequences with challenging lighting and occlusion conditions.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Task-Driven Feedback Imager with Uncertainty Driven Hybrid Control

Mudassar

Saha

Wolf

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Deep Neural Network (DNN) systems tend to produce overconfident or uncalibrated outputs. This poses problems for active sensor systems that have a DNN module as the main feedback controller. In this paper, we study a closed-loop feedback smart camera from the lens of uncertainty estimation. The uncertainty of the task output is used to characterize and facilitate the feedback operation. The DNN uncertainty in the feedback system is estimated and characterized using both sampling and non-sampling based methods. In addition, we propose a closed-loop control that incorporates uncertainty information when providing feedback. We show two modes of control, one that prioritizes false positives and one that prioritizes false negatives, and a hybrid approach combining the two. We apply the uncertainty-driven control to the tasks of object detection, object tracking, and action detection. The hybrid system improves object detection and tracking accuracy on the CAMEL dataset by 1.1% each respectively. For the action detection task, the hybrid approach improves accuracy by 1.4%.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The new uncertainty-driven control (Figure 2) improves performance for false negatives on the CAMEL dataset [13] for the tasks of object detection and tracking. The CAMEL dataset contains RGB-IR videos with pedestrians and cars annotated.…”

mentioning

confidence: 99%

A Task-Driven Feedback Imager with Uncertainty Driven Hybrid Control

Mudassar

Saha

Wolf

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Alternatively, images can be recorded with the same optical axis through the use of a beam-splitter. This removes the need for alignment/correspondence estimation and applies to RGB/NIR datasets EFPL [21], RANUS [29], and also RGB/FIR datasets KAIST [13], Coaxials [14], CAMEL [15].…”

Section: A Multispectral Datasetsmentioning

confidence: 99%

“…This is partially due to the availability and cost of sensors, in addition to the complications of solving the correspondence problem when photometric consistency between sensors does not hold true. Most multispectral datasets/methods purposefully avoid tackling stereo disparity, by either focusing on scenes at long range, where disparity is assumed to be negligible [12], or by using a beam splitter to ensure coaxial camera centres [13]- [15]. Unfortunately both approaches ignore possible stereo cues.…”

Section: Introductionmentioning

confidence: 99%

There and Back Again: Self-supervised Multispectral Correspondence Estimation

Walters¹,

Méndez²,

Johnson³

et al. 2021

Preprint

View full text Add to dashboard Cite

Across a wide range of applications, from autonomous vehicles to medical imaging, multi-spectral images provide an opportunity to extract additional information not present in color images. One of the most important steps in making this information readily available is the accurate estimation of dense correspondences between different spectra.Due to the nature of cross-spectral images, most correspondence solving techniques for the visual domain are simply not applicable. Furthermore, most cross-spectral techniques utilize spectra-specific characteristics to perform the alignment. In this work, we aim to address the dense correspondence estimation problem in a way that generalizes to more than one spectrum. We do this by introducing a novel cycle-consistency metric that allows us to self-supervise. This, combined with our spectraagnostic loss functions, allows us to train the same network across multiple spectra.We demonstrate our approach on the challenging task of dense RGB-FIR correspondence estimation. We also show the performance of our unmodified network on the cases of RGB-NIR and RGB-RGB, where we achieve higher accuracy than similar self-supervised approaches. Our work shows that crossspectral correspondence estimation can be solved in a common framework that learns to generalize alignment across spectra.

show abstract

“…It may also contain a stack of sub-images that is not the case with the existing medical datasets. In addition, general VQA datasets (Lin et al, 2014;Mukuze et al, 2018;Gebhardt & Wolf, 2018;Antol et al, 2015) are task-specific, unlike VQA-Med, where a question can be asked about any disease from any part of the body.…”

Section: Datasetsmentioning

confidence: 99%

Hierarchical Deep Multi-modal Network for Medical Visual Question Answering

Gupta¹,

Suman²,

Ekbal³

2020

Preprint

View full text Add to dashboard Cite

Visual Question Answering in Medical domain (VQA-Med) plays an important role in providing medical assistance to the end-users. These users are expected to raise either a straightforward question with a Yes/No answer or a challenging question that requires a detailed and descriptive answer. The existing techniques in VQA-Med fail to distinguish between the different question types sometimes complicates the simpler problems, or over-simplifies the complicated ones. It is certainly true that for different question types, several distinct systems can lead to confusion and discomfort for the end-users. To address this issue, we propose a hierarchical deep multi-modal network that analyzes and classifies end-user questions/queries and then incorporates a query-specific approach for answer prediction. We refer our proposed approach as Hierarchical Question Segregation based Visual Question Answering, in short HQS-VQA. Our contributions are three-fold, viz. firstly, we propose a question segregation (QS) technique for VQA-Med; secondly, we integrate the QS model to the hierarchical deep multi-modal neural network to generate proper answers to the queries related to medical images; and thirdly, we study the impact of QS in Medical-VQA by comparing the performance of the proposed model with QS and a model without QS. We evaluate the performance of our proposed model on two benchmark datasets, viz.

show abstract

CAMEL Dataset for Visual and Thermal Infrared Multiple Object Detection and Tracking

Cited by 46 publications

References 19 publications

A Task-Driven Feedback Imager with Uncertainty Driven Hybrid Control

A Task-Driven Feedback Imager with Uncertainty Driven Hybrid Control

There and Back Again: Self-supervised Multispectral Correspondence Estimation

Hierarchical Deep Multi-modal Network for Medical Visual Question Answering

Contact Info

Product

Resources

About