Multiple 3D Object tracking for augmented reality

By Youngmin Park, Vincent Lepetit, Woontack Woo. 2008

176 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Jiaya Jia
2. Shu Liu
3. Silvio Savarese
4. Yin Zhou
5. Zetong Yang
6. Yanan Sun
7. Jie Zhou
8. Xiaoyong Shen

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Ming-Hsuan Yang
3. Xiaogang Wang
4. Dacheng Tao
5. Jitendra Malik
6. Trevor Darrell
7. Chunhua Shen
8. Li Fei-Fei

Citations in the corpus

• VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection (2017, background): “Point cloud based 3D object detection is an important component of a variety of real-world applications, such as autonomous navigation [11, 14], housekeeping robots [28], and augmented/virtual reality [29].”
• KETO: Learning Keypoint Representations for Tool Manipulation (2019, background): “The idea of using point-based representations has been widely explored in domains such as visual recognition [36], tracking [43], and reinforcement”
• STD: Sparse-to-Dense 3D Object Detector for Point Cloud (2019, background): “3D scene understanding from point clouds is a very important topic in computer vision, since it benefits many applications, such as autonomous driving [8] and augmented reality [24].”
• Pose Estimation for Augmented Reality: A Hands-On Survey (2016, unknown): “A non-linear minimization technique is for example considered in [96], [144] using SIFT and FERNS.”
• FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds (2019, background): “3D object detection [3, 4, 10, 32, 24, 13] has become increasingly important in many fields, such as autonomous driving [1], mobile robots [27] and virtual/augmented reality [17].”
• MVX-Net: Multimodal VoxelNet for 3D Object Detection (2019, background): “A wide variety of applications such as augmented reality [26], robotics [25], and navigation [11],”
• Revisiting Trends in Augmented Reality Research: A Review of the 2nd Decade of ISMAR (2008–2017) (2018, background): “[106] showed how to track multiple occluding 3D objects, and Roussos et al.”
• 3DSSD: Point-Based 3D Single Stage Object Detector (2020, background): “3D scene understanding has attracted much attention since it benefits many applications, such as autonomous driving [7] and augmented reality [17].”
• IPOD: Intensive Point-based Object Detector for Point Cloud (2018, unknown): “Meanwhile, 3D scene understanding with point cloud also becomes an important topic, since it can benefit many applications, such as autonomous driving [13] and augmented reality [27].”
• Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking (2011, background): “Tracking of arbitrary, but a priori known targets has been demonstrated despite occlusion and even deformation (Lepetit and Fua 2006), for multiple targets (Park et al. 2008), and even on current generation mobile phones (Wagner et al. 2008, 2009).”
• 3D Object Detection with Pointformer (2020, background): “3D object detection in point clouds is essential for many real-world applications such as autonomous driving [10] and augmented reality [18].”
• Multiple object tracking: A literature review (2014, background): “3D tracking [168], which could provide more accurate position, size estimation and effective occlusion handling for highlevel computer vision tasks, is potentially more useful.”