AUTO-G: Gesture Recognition in the Crowd for Autonomous Vehicl

Tripathi, Pavani; Keshari, Rohit; Ghosh, Subhradip; Vatsa, Mayank; Singh, Richa

doi:10.1109/icip.2019.8803692

Cited by 6 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Fig. 1, articulated pose can be utilized to generate an appearance-invariant intermediate representation and is widely supported in literature for modeling VRU behavior like action recognition (Hariyono and Jo 2015), crossing intention estimation (Fang and López 2019), trajectory prediction (Rasouli et al 2019) and gesture recognition (Tripathi et al 2019). Even though there have been great strides in human pose estimation, there has been less focus from the perspective of real-time applications such as AD usecases (Kothari et al 2017) (Kress et al 2018).…”

Section: Introductionmentioning

confidence: 99%

VRU Pose-SSD: Multiperson Pose Estimation For Automated Driving

Kumar¹,

Ramesh²,

Chakraborty³

et al. 2021

AAAI

View full text Add to dashboard Cite

We present a fast and efficient approach for joint person detection and pose estimation optimized for automated driving (AD) in urban scenarios. We use a multitask weight sharing architecture to jointly train detection and pose estimation. This modular architecture allows us to accommodate different downstream tasks in the future. By systematic large-scale experiments on the Tsinghua-Daimler Urban Pose Dataset (TDUP), we obtain multiple models with varying accuracy-speed trade-offs. We then quantize and optimize our network for deployment and present a detailed analysis of the efficacy of the algorithm. We introduce a two-stage evaluation strategy, which is more suitable for AD and achieve a significant performance improvement in comparison to state-of-the-art approaches. Our optimized model runs at 52~fps on full HD images and still reaches a competitive performance of 32.25~LAMR. We are confident that our work serves as an enabler to tackle higher-level tasks like VRU intention estimation and gesture recognition, which rely on stable pose estimates and will play a crucial role in future AD systems.

show abstract

Section: Introductionmentioning

confidence: 99%

VRU Pose-SSD: Multiperson Pose Estimation For Automated Driving

Kumar¹,

Ramesh²,

Chakraborty³

et al. 2021

AAAI

View full text Add to dashboard Cite

show abstract

“…This is an extremely challenging and a time-consuming task. The various components which significantly influence the performance of real-world recognitions are computational expense, rapid actions, change in lighting conditions, soul-occlusion, unpredictable environments and a large number in degree of freedom (DOF) [5].…”

Section: Introductionmentioning

confidence: 99%

Precise Recognition of Vision Based Multi-hand Signs Using Deep Single Stage Convolutional Neural Network

Bose

Kumar

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

The precise recognition of multi-hand signs in real-time under dynamic backgrounds, illumination conditions is a time consuming process. In this paper, a time efficient single stage convolutional neural network (CNN) You Only Look Once (YOLO-V2) model is proposed for real-time multi-hand sign recognition. The model utilizes DarkNet-19 CNN architecture as a feature extractor. The model is trained and tested on three distinct datasets (NUSHP-II, SENZ-3D and MITI-HD). The range of IoU from 0.5 to 0.95, the model is validated using test dataset. For the MITI-HD, the YOLO-V2 CNN model obtained an average precision value of 99.10% for AP 0.5 ; 93.00% for AP 0.75 and 78.30% for AP 0.5:0.95 . The Adam Optimizer on YOLO-V2 CNN model supersedes the other optimization methods. The prediction time of YOLO-V2 CNN is obtained as 20 ms, much lower than other single-stage hand sign recognition systems.

show abstract