Example-Based 3D Trajectory Extraction of Objects From 2D Videos

Boukhers, Zeyd; Shirahama, Kimiaki; Grzegorzek, Marcin

doi:10.1109/tcsvt.2017.2727963

Cited by 5 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1, we make the following observations: (1) Our method outperforms all the baselines and competitors, establishing new state-of-the-art with 74.1%, 84.3% and 86.8% on 1-shot, 3-shot and 5-shot settings, respectively. (2) We notice that the strong baseline "RGB Basenet++" is superior to "RGB Basenet", which is mainly contributed by our basic sampling strategy (section 3.3). It quite makes sense, since the clips of length 𝑛𝑢𝑚 𝑠𝑒𝑔 * 𝑛𝑢𝑚 𝑓 sampled by our method capture more temporal information, especially in the case of long-term videos.…”

Section: Results On Kineticsmentioning

confidence: 93%

“…To the best of our knowledge, we are the first to introduce depth as the carrier of scene information for video recognition under few-shot learning. Note that [2] estimates the depth to correct the camera odometry. Most of the multi-modality models simply fuse the features from different streams by averaging [45], concatenation [56], recurrent neural networks [69] or with fully connected layers [21], while we adaptively learn how to combine the RGB stream and depth stream by introducing a novel depth guided adaptive instance normalization module.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition

Zhang

Wang

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Figure 1: Concept: depth information helps to model the relation between the moving person and the scene, thus guiding to learn richer context and less biased representation. We observe two important characteristics: 1) Apparently, scene information helps us to recognize actions. In this example, the mountain is critical to identifying the action as "riding mountain bike". 2) Even if the scene shifts from the mountain to the roadside, we can still recognize it correctly. The example is sampled from the Kinetics dataset.

show abstract

Section: Results On Kineticsmentioning

confidence: 93%

Section: Related Workmentioning

confidence: 99%

Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition

Zhang

Wang

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…The existing approach offers importance to extracting the semantic factor associated with capturing essential features for performing the track. Boukhers et al [22] have discussed a probability-based model for obtaining trajectories of a threedimensional object from two-dimensional video feeds. The model can estimate the object depth from the calculated focal length.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Unusual Event Tracking in Video Sequence using Block Shift Feature Algorithm

Kumar¹,

Kavya²

2022

IJACSA

View full text Add to dashboard Cite

The area of video technology is rapidly growing owing to advancements in intelligent video systems in sensor operations, higher bandwidth capacity, storage, and highresolution displays. This led to the proliferation of video-based computing modeling to perform specific tasks on video sequences to gain more insight from the data. Visual tracking of events is a core component in video visual surveillance systems that classify and track moving objects to describe their behavioral aspects. The prime motive behind intelligent video systems is to perform efficient video analytics to meet the specific requirements of the user/use-cases. It involves a self-directed paradigm to understand event sequences, reducing the computational burden of characterizing the activities. The study incorporates a block-shift feature algorithm and introduces a novel computational research method for unusual event tracking in video sequences. The formulated approach employs a framework combining operational blocks to compute sequential operations such as block-matching from the dictionary of motion estimations. Before applying the learning model, the subsequent analysis procedure adds feature lexicon and dominant attributes to make the execution computationally efficient. Further, it uses a sparsenon negative factorization approach to organize the informative details into k possible finite clusters. The event detection outcome from the training datasets of video sequences shows better experimental results than the traditional highly cited related approach of unusual object detection and tracking.

show abstract

“…The key factor of system quality is to know the exact present position of a vehicle, and to predict its future position accurately by monitoring the movement of a vehicle for collision avoidance [4] [5].…”

Section: Introductionmentioning

confidence: 99%

Vehicle Intersection Collision Monitoring Algorithm Based on VANETs and Uncertain Trajectory

Ding¹,

Wu²,

Dong³

et al. 2018

EasyChair Preprints

View full text Add to dashboard Cite

Abstract-In order to ensure driving safely, the driving safety assistance system must be able to aware of potential collision accidents in advance, especially significant for the intersection where traffic accidents occur more frequently. Considering that VANETs is one of the most important applications for improving the safety of driving, furthermore, vehicles have an inherent uncertainty of location because the exact position of a moving object is known, with certainty, only at the time of an update on position information. In order to reduce the accident rate at intersection and combine the driving characteristics of vehicles at traffic intersections, a vehicle intersection collision monitoring algorithm based on VANETs and uncertain trajectory is proposed. The algorithm is divided into two categories: uncertain trajectory prediction algorithm and vehicle collision monitoring algorithm. The proposed approach provides approximate answers to the user at the users required level of accuracy while achieving near-optimal communication and computational costs. Finally, extensive experiments were conducted to show the efficiency and efficacy of the proposed approach.

show abstract

Example-Based 3D Trajectory Extraction of Objects From 2D Videos

Cited by 5 publications

References 28 publications

Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition

Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition

An Efficient Unusual Event Tracking in Video Sequence using Block Shift Feature Algorithm

Vehicle Intersection Collision Monitoring Algorithm Based on VANETs and Uncertain Trajectory

Contact Info

Product

Resources

About