A wearable obstacle avoidance device for visually impaired individuals with cross-modal learning by Yun Gao, Dan Wu, Jie Song, Xueyi Zhang, Bangbang Hou, Hengfa Liu, Junqi Liao, Liang Zhou

Get full text

Improving Monocular Depth Estimation Through Knowledge Distillation: Better Visual Quality and Efficiency by Chang Yeop Lee, Dong Ju Kim, Young Joo Suh, Do Kyung Hwang

“…This paper introduces a novel knowledge distillation (KD) framework for monocular depth estimation (MDE), incorporating dynamic weight adaptation to address critical challenges. The proposed approach effectively mitigates visual limitations, including blurred object boundaries and discontinuous artifacts, while preserving quantitative performance. …”
Get full text

Scalable video coding algorithm based on 3D hybrid tree and visual characteristics by Ming-zhe FU, Xiang-hai WANG, Chuan-ming SONG

“…The distribution characteristic of three-dimensional wavelet coefficients of video data was ana ed,and a scalable video coding algorithm was subsequently addressed based on hybrid three-dimensional tree and human visual system (HVS) characteristics.First,the hybrid tree structure was adaptively determined according to the auto-correlation of low-pass and high-pass coefficients.It reduced obviously the number of ion bits locating significant wavelet coefficients when scanning and processing low-pass and high-pass coefficients in temporal dimension.Second,each wavelet coefficient was weighted in terms of HVS sensitivity to its corresponding subband.Significant coefficients thus tended to be coded with high priority and arranged at the front of bitstream,and the reconstructed video quality was improved at low and medium bitrates to a great extent.Experimental results in terms of peak signal-to-noise ratio (PSNR) verified the effectiveness of the proposed algorithm on several test videos with varying characteristics.0.65dB,1.75dB,and 1.77dB higher PSNR are gained than asymmetric 3-D orientation tree for Y,U,and V components,respectively.Moreover,0.23dB,2.11dB,and 1.72dB higher PSNR are reached than single temporal-spatial orientation tree separately for Y,U,and V components.Besides,better subjective quality is obtained through effectively attenuating ringing artifact.…”
Get full text

Scalable video coding algorithm based on 3D hybrid tree and visual characteristics by Ming-zhe FU, Xiang-hai WANG, Chuan-ming SONG

“…The distribution characteristic of three-dimensional wavelet coefficients of video data was ana ed,and a scalable video coding algorithm was subsequently addressed based on hybrid three-dimensional tree and human visual system (HVS) characteristics.First,the hybrid tree structure was adaptively determined according to the auto-correlation of low-pass and high-pass coefficients.It reduced obviously the number of ion bits locating significant wavelet coefficients when scanning and processing low-pass and high-pass coefficients in temporal dimension.Second,each wavelet coefficient was weighted in terms of HVS sensitivity to its corresponding subband.Significant coefficients thus tended to be coded with high priority and arranged at the front of bitstream,and the reconstructed video quality was improved at low and medium bitrates to a great extent.Experimental results in terms of peak signal-to-noise ratio (PSNR) verified the effectiveness of the proposed algorithm on several test videos with varying characteristics.0.65dB,1.75dB,and 1.77dB higher PSNR are gained than asymmetric 3-D orientation tree for Y,U,and V components,respectively.Moreover,0.23dB,2.11dB,and 1.72dB higher PSNR are reached than single temporal-spatial orientation tree separately for Y,U,and V components.Besides,better subjective quality is obtained through effectively attenuating ringing artifact.…”
Get full text

Seg-Eigen-CAM: Eigen-Value-Based Visual Explanations for Semantic Segmentation Models by Ching-Ting Chung, Josh Jia-Ching Ying

“…As an extension of Grad-CAM, several methods have been proposed and applied to image segmentation with the aim of enhancing existing techniques and adapting their properties. However, in this study, we highlight a common issue with gradient-based methods when generating visual explanations—these methods tend to emphasize background information, resulting in significant noise, especially when dealing with image segmentation tasks involving complex or cluttered backgrounds. …”
Get full text

Enhanced lightweight infrared object detection algorithm for assistive navigation in visually impaired individuals by Zhimin Bai, Yang Yang, Jian Wang, Zhengyang Li, Jiajun Wang, Chunxin Liu

“…A distinctive feature of the approach is its monocular distance and velocity measurement integration, which operates independently of external devices, providing direct navigation support for visually impaired people. Further, the enhanced YOLOv8 is adapted for mobile use, employing pruning and lightweight methods, which substantially enhance its practicality. …”
Get full text

Exploring Heterogeneity in Car-Following Behaviors Based on Driver Visual Characteristics: Modeling and Calibration by Congcong Bai, Jun Jing, Bokun Liu, Wenbin Yao, Chengcheng Yang, Adjé Jérémie Alagbé, Sheng Jin

“…Firstly, all the effective vehicle trajectories were extracted and categorized into different vehicle types based on their widths, resulting in four combination types of car-following segments. Visual angle and its change rate were introduced as variables representing driver visual characteristics. …”
Get full text

DK-SLAM: Monocular Visual SLAM with Deep Keypoint Learning, Tracking, and Loop Closing by Hao Qu, Lilian Zhang, Jun Mao, Junbo Tie, Xiaofeng He, Xiaoping Hu, Yifei Shi, Changhao Chen

“…The performance of visual SLAM in complex, real-world scenarios is often compromised by unreliable feature extraction and matching when using handcrafted features. …”
Get full text

E-CLIP: An Enhanced CLIP-Based Visual Language Model for Fruit Detection and Recognition by Yi Zhang, Yang Shao, Chen Tang, Zhenqing Liu, Zhengda Li, Ruifang Zhai, Hui Peng, Peng Song

“…This problem stems from their reliance on unimodal visual data, which creates a semantic gap between image features and contextual understanding. …”
Get full text

Relationship Between Refractive Error, Visual Acuity, and Postural Stability in Elite Football Players by Miguel Oliveira, Rui Fuste, Javier Gene-Morales, Andrés Gené-Sampedro, Jorge Jorge

“…This study aimed to investigate the relationship between visual system parameters (visual acuity and refractive error) and postural balance under controlled conditions in elite football players. …”
Get full text

228 Visualizing impact: Operationalizing community engagement evaluation using the RE-AIM framework by Brian Do-Golden, Nicole Wolfe, Nicole MG Maccalla, Michele D. Kipke

“…Scores were mapped in net effect diagrams in the form of radar charts to enable comparative analysis and visualization, highlighting a variety of grouped variables (i.e., language, locations, and adaptation). …”
Get full text

Neural signature of chronic migraine mice model and related photophobia in the primary visual cortex by Kai-Bo Zhang, Cheng Peng, Zhen Liu, Sheng-Lin Zhao, Chen-Lu Zhu, Shou-Yi Wu, Tian-Xiao Wang, Zhi-Lei Li, Jing-Gui Gao, Yun-Hao Xu, Tian-Hua Fan, Hong Xie, Ji-Song Guan, Yong-Gang Wang

“…Neuroimaging investigations have revealed that the primary visual cortex exhibits abnormal activation patterns both during and between migraine attacks. …”
Get full text

Visual SLAM algorithm for underground robots in coal mines based on point-line features by Li WANG, Tianxiang ZANG, Bo SU

“…In the application of visual SLAM(Simultaneous Localization and Mapping) in coal mines, lighting changes and low-texture scenes seriously affect the extraction and matching of feature points, resulting in the failure of pose estimation and affecting the positioning accuracy. …”
Get full text

Wandering around: a bioinspired approach to visual attention through object motion sensitivity by Giulia D’Angelo, Victoria Clerico, Chiara Bartolozzi, Matej Hoffmann, P Michael Furlong, Alexander Hadjiivanov

“…To distinguish moving objects while the event-based camera is also in motion, the agent requires an object motion segmentation mechanism to accurately detect targets and position them at the centre of the visual field (fovea). Integrating event-based sensors with neuromorphic algorithms represents a paradigm shift, using spiking neural networks (SNNs) to parallelise computation and adapt to dynamic environments. …”
Get full text

Improving Visual Field Awareness among Collegiate Softball Athletes: A Randomized Trial by Diana R. Feldhacker, Whitney Lucas Molitor

“…The results from this study demonstrate the adaptability of the visual system for those with normal field of vision.…”
Get full text

Depicting Gender Construction in Visual Images of ELT Textbook of Junior High School in Indonesia by Monika Saraswati, Yokke Andini

“…Penelitian ini memiliki dua tujuan: (1) untuk mengetahui konstruksi gender dalam gambar visual yang terdapat pada buku pelajaran Bahasa Inggris kelas IX SMP yang diterbitkan oleh Kementerian Pendidikan dan Kebudayaan Republik Indonesia; (2) menjelaskan representasi bias dan stereotip gender dalam gambar visual buku pelajaran Bahasa Inggris kelas IX SMP yang diterbitkan oleh Kementerian Pendidikan dan Kebudayaan Republik Indonesia. …”
Get full text

Movement Impairments May Not Preclude Visuomotor Adaptation After Stroke by Robert Taylor Moore, Mark Andrew Piitz, Nishita Singh, Sean Peter Dukelow, Tyler Cluff

“…Learning was quantified as the extent to which the participants adapted their movements to the visual disturbance. …”
Get full text

A formal statechart model of immediate neonatal adaptation guidelines by Edgar Hernando Sepúlveda-Oviedo, Leonardo Enrique Bermeo Clavijo, Luis Carlos Méndez–Córdoba

“…Feedback indicates general satisfaction with the Versatility, Usability, Scalability and Moderate visual complexity of the model.…”
Get full text

Adaptive Monitoring Relevance in Camera Networks for Critical Surveillance Applications by Daniel G. Costa, Luiz Affonso Guedes, Francisco Vasques, Paulo Portugal

Get full text

A Design of Adaptive Quantizer for MPEG-2 Video Coding by 孙军, 张文军, 余松煜

“…Based upon studying the strategy for adaptive quantization suggested by MPEG-2 Test Model 5,a new quantizer is presented in this paper.Block-based visual activities are analyzed to exploit local perceptual characteristics in the macroblock.In order to decide the adaptive perceptual quantization factor,macroblock characteristic is identified by evaluating comprehensively each block’s local activity within this macroblock.Experiment results show that coding distortion is uniformly distributed across the image with the proposed quantizer ,and picture quality is improved. …”
Get full text