Fast and Accurate Camera Scene Detection on Smartphones
- URL: http://arxiv.org/abs/2105.07869v1
- Date: Mon, 17 May 2021 14:06:21 GMT
- Title: Fast and Accurate Camera Scene Detection on Smartphones
- Authors: Angeline Pouget, Sidharth Ramesh, Maximilian Giang, Ramithan
Chandrapalan, Toni Tanner, Moritz Prussing, Radu Timofte, Andrey Ignatov
- Abstract summary: This paper proposes a novel Camera Scene Detection dataset (CamSDD) containing more than 11K manually crawled images.
We propose an efficient and NPU-friendly CNN model for this task that demonstrates a top-3 accuracy of 99.5% on this dataset.
- Score: 51.424407411660376
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: AI-powered automatic camera scene detection mode is nowadays available in
nearly any modern smartphone, though the problem of accurate scene prediction
has not yet been addressed by the research community. This paper for the first
time carefully defines this problem and proposes a novel Camera Scene Detection
Dataset (CamSDD) containing more than 11K manually crawled images belonging to
30 different scene categories. We propose an efficient and NPU-friendly CNN
model for this task that demonstrates a top-3 accuracy of 99.5% on this dataset
and achieves more than 200 FPS on the recent mobile SoCs. An additional
in-the-wild evaluation of the obtained solution is performed to analyze its
performance and limitation in the real-world scenarios. The dataset and
pre-trained models used in this paper are available on the project website.
Related papers
- Redundancy-Aware Camera Selection for Indoor Scene Neural Rendering [54.468355408388675]
We build a similarity matrix that incorporates both the spatial diversity of the cameras and the semantic variation of the images.
We apply a diversity-based sampling algorithm to optimize the camera selection.
We also develop a new dataset, IndoorTraj, which includes long and complex camera movements captured by humans in virtual indoor environments.
arXiv Detail & Related papers (2024-09-11T08:36:49Z) - Robust Frame-to-Frame Camera Rotation Estimation in Crowded Scenes [8.061773364318313]
We present an approach to estimating camera rotation in crowded, real-world scenes from handheld monocular video.
We provide a new dataset and benchmark, with high-accuracy, rigorously verified ground truth, on 17 video sequences.
This represents a strong new performance point for crowded scenes, an important setting for computer vision.
arXiv Detail & Related papers (2023-09-15T17:44:07Z) - Efficient Single Object Detection on Image Patches with Early Exit
Enhanced High-Precision CNNs [0.0]
This paper proposes a novel approach for detecting objects using mobile robots in the context of the RoboCup Standard Platform League.
The challenge lies in detecting a dynamic object in varying lighting conditions and blurred images caused by fast movements.
To address this challenge, the paper presents a convolutional neural network architecture designed specifically for computationally constrained robotic platforms.
arXiv Detail & Related papers (2023-09-07T07:23:55Z) - CabiNet: Scaling Neural Collision Detection for Object Rearrangement
with Procedural Scene Generation [54.68738348071891]
We first generate over 650K cluttered scenes - orders of magnitude more than prior work - in diverse everyday environments.
We render synthetic partial point clouds from this data and use it to train our CabiNet model architecture.
CabiNet is a collision model that accepts object and scene point clouds, captured from a single-view depth observation.
arXiv Detail & Related papers (2023-04-18T21:09:55Z) - Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022
challenge: Report [75.79829464552311]
This challenge was to develop an efficient end-to-end AI-based rendering approach that can run on modern smartphone models.
The resulting model was evaluated on the Kirin 9000's Mali GPU that provides excellent acceleration results for the majority of common deep learning ops.
arXiv Detail & Related papers (2022-11-07T22:42:02Z) - BCOT: A Markerless High-Precision 3D Object Tracking Benchmark [15.8625561193144]
We present a multi-view approach to estimate the accurate 3D poses of real moving objects, and then use binocular data to construct a new benchmark for monocular textureless 3D object tracking.
Based on our object-centered model, we jointly optimize the object pose by minimizing shape re-projection constraints in all views.
Our new benchmark dataset contains 20 textureless objects, 22 scenes, 404 video sequences and 126K images captured in real scenes.
arXiv Detail & Related papers (2022-03-25T03:55:03Z) - Bridging the Gap between Events and Frames through Unsupervised Domain
Adaptation [57.22705137545853]
We propose a task transfer method that allows models to be trained directly with labeled images and unlabeled event data.
We leverage the generative event model to split event features into content and motion features.
Our approach unlocks the vast amount of existing image datasets for the training of event-based neural networks.
arXiv Detail & Related papers (2021-09-06T17:31:37Z) - Fast and Accurate Quantized Camera Scene Detection on Smartphones,
Mobile AI 2021 Challenge: Report [65.91472671013302]
We introduce the first Mobile AI challenge, where the target is to develop quantized deep learning-based camera scene classification solutions.
The proposed solutions are fully compatible with all major mobile AI accelerators and can demonstrate more than 100-200 FPS on the majority of recent smartphone platforms.
arXiv Detail & Related papers (2021-05-17T13:55:38Z) - CoordiNet: uncertainty-aware pose regressor for reliable vehicle
localization [3.4386226615580107]
We investigate visual-based camera localization with neural networks for robotics and autonomous vehicles applications.
Our solution is a CNN-based algorithm which predicts camera pose directly from a single image.
We show that our proposal is a reliable alternative, achieving 29cm median error in a 1.9km loop in a busy urban area.
arXiv Detail & Related papers (2021-03-19T13:32:40Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.