Object Viewpoint Classification Based 3D Bounding Box Estimation for Autonomous Vehicles

Lingtao, Zhou; Fang, Jiaojiao; Liu, Guizhong

doi:10.48550/arxiv.1909.01025

Cited by 5 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Discussion. It's worth noting that generating view labels for videos in 𝐷 3rd is straightforward with the help of an off-the-shelf view classifier similar to Zhou et al [37] but towards the human body. Therefore, by expanding the pre-training data with view labels, we can expect to achieve better view-agnostic representation.…”

Section: Discussionmentioning

confidence: 99%

“…Therefore, in this phase, we aim to train POV to learn view-agnostic representation from multi-view videos via view-aware prompts. Please note that the view labels, if not available, can be identified inexpensively using an off-the-shelf view classifier [37]. Meanwhile, there exist multiple third-person video corpora that contain different camera view angles, such as Kinetics [25], TSU [6], and NTU [38], which can all be leveraged for learning view-agnostic knowledge.…”

Section: View-agnostic Prompt Tuningmentioning

confidence: 99%

See 1 more Smart Citation

POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-view World

Xu,

Zheng,

Jin

2023

Proceedings of the 31st ACM International Conference on Multimedia

View full text Add to dashboard Cite

We humans are good at translating third-person observations of hand-object interactions (HOI) into an egocentric view. However, current methods struggle to replicate this ability of view adaptation from third-person to first-person. Although some approaches attempt to learn view-agnostic representation from large-scale video datasets, they ignore the relationships among multiple third-person views. To this end, we propose a Prompt-Oriented View-agnostic learning (POV) framework in this paper, which enables this view adaptation with few egocentric videos. Specifically, We introduce interactive masking prompts at the frame level to capture finegrained action information, and view-aware prompts at the token level to learn view-agnostic representation. To verify our method, we establish two benchmarks for transferring from multiple thirdperson views to the egocentric view. Our extensive experiments on these benchmarks demonstrate the efficiency and effectiveness of our POV framework and prompt tuning techniques in terms of view adaptation and view generalization. Our code is available at https://github.com/xuboshen/pov_acmmm2023. CCS CONCEPTS• Computing methodologies → Activity recognition and understanding; Scene understanding; Transfer learning.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: View-agnostic Prompt Tuningmentioning

confidence: 99%

POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-view World

Xu,

Zheng,

Jin

2023

Proceedings of the 31st ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…Others use the ability of deep neural networks to learn complex features from images to generate 2D box proposals [56], [57].…”

Section: Image 3d Object Detection Methods and Comparison Of Various ...mentioning

confidence: 99%

Deep Learning-Based Image 3-D Object Detection for Autonomous Driving: Review

Alaba

Ball

2023

IEEE Sensors J.

View full text Add to dashboard Cite

An accurate and robust perception system is key to understanding the driving environment of autonomous driving and robots. Autonomous driving needs 3D information about objects, including the object's location and pose, to understand the driving environment clearly. A camera sensor is widely used in autonomous driving because of its richness in color and texture and low price. The major problem with the camera is the lack of 3D information, which is necessary to understand the 3D driving environment. Additionally, the object's scale change and occlusion make 3D object detection more challenging. Many deep learning-based methods, such as depth estimation, have been developed to solve the lack of 3D information. This survey presents the image 3D object detection 3D bounding box encoding techniques and evaluation metrics. The image-based methods are categorized based on the technique used to estimate an image's depth information, and insights are added to each method. Then, state-of-the-art (SOTA) monocular and stereo camera-based methods are summarized. We also compare the performance of the selected 3D object detection models and present challenges and future directions in 3D object detection.

show abstract

“…The classic object detection methods use hand-crafted methods to generate 2D box proposals [47]- [50]. Others use the ability of deep neural networks to learn complex features from images to generate 2D box proposals [51], [52]. Similarly, the box proposals can be generated from geometric constraints [53], [54], pseudo-LiDAR [46], [55] or stereo depth estimation [3], [56].…”

Section: Image 3d Object Detection Methods and Comparison Of Various ...mentioning

confidence: 99%

Deep Learning-based Image 3D Object Detection for Autonomous Driving: Review

Alaba¹,

Ball²

2022

Preprint

View full text Add to dashboard Cite

<p>An accurate and robust perception system is key to understanding the driving environment of autonomous driving and robots. Autonomous driving needs 3D information about objects, including the object’s location and pose, to understand the driving environment clearly. A camera sensor is widely used in autonomous driving because of its richness in color, texture, and low price. The major problem with the camera is the lack of 3D information, which is necessary to understand the 3D driving environment. Additionally, the object’s scale change and cclusion make 3D object detection more challenging. Many deep learning-based methods, such as depth estimation, have been developed to solve the lack of 3D information. This survey presents the image 3D object detection 3D bounding box encoding techniques, feature extraction techniques, and evaluation metrics of 3D object detection. The image-based methods are categorized based on the technique used to estimate an image’s depth information, and insights are added to each method. Then, state-of-the-art (SOTA) monocular and stereo camera-based methods are summarized. We also compare the performance of the selected 3D object detection models and present challenges and future directions in 3D object detection.</p>

show abstract

Object Viewpoint Classification Based 3D Bounding Box Estimation for Autonomous Vehicles

Cited by 5 publications

References 0 publications

POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-view World

POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-view World

Deep Learning-Based Image 3-D Object Detection for Autonomous Driving: Review

Deep Learning-based Image 3D Object Detection for Autonomous Driving: Review

Contact Info

Product

Resources

About