Several studies in computer vision have examined specular removal, which is crucial for object detection and recognition. This research has traditionally been divided into two tasks: specular ...highlight removal, which focuses on removing specular highlights on object surfaces, and reflection removal, which deals with specular reflections occurring on glass surfaces. In reality, however, both types of specular effects often coexist, making it a fundamental challenge that has not been adequately addressed. Recognizing the necessity of integrating specular components handled in both tasks, we constructed a specular-light (S-Light) DB for training single-image-based deep learning models. Moreover, considering the absence of benchmark datasets for quantitative evaluation, the multi-scale normalized cross correlation (MS-NCC) metric, which considers the correlation between specular and diffuse components, was introduced to assess the learning outcomes.
With the increase of large camera networks around us, it is becoming more difficult to manually identify vehicles. Computer vision enables us to automate this task. More specifically, vehicle ...re-identification (ReID) aims to identify cars in a camera network with non-overlapping views. Images captured of vehicles can undergo intense variations of appearance due to illumination, pose, or viewpoint. Furthermore, due to small inter-class similarities and large intra-class differences, feature learning is often enhanced with non-visual cues, such as the topology of camera networks and temporal information. These are, however, not always available or can be resource intensive for the model. Following the success of Transformer baselines in ReID, we propose for the first time an outlook-attention-based vehicle ReID framework using the Vision Outlooker as its backbone, which is able to encode finer-level features. We show that, without embedding any additional side information and using only the visual cues, we can achieve an 80.31% mAP and 97.13% R-1 on the VeRi-776 dataset. Besides documenting our research, this paper also aims to provide a comprehensive walkthrough of vehicle ReID. We aim to provide a starting point for individuals and organisations, as it is difficult to navigate through the myriad of complex research in this field.
The popularity of Agrocybe cylindracea is increasing due to its unique flavor and nutritional value. The Agrocybe cylindracea cap is a key aspect of the growth process, and high-throughput ...observation of cap traits in greenhouses by machine vision is a future development trend of smart agriculture. Nevertheless, the segmentation of the Agrocybe cylindracea cap is extremely challenging due to its similarity in color to the rest of the mushroom and the occurrence of mutual occlusion, presenting a major obstacle for the effective application of automation technology. To address this issue, we propose an improved instance segmentation network called Agrocybe cylindracea R-CNN (AC R-CNN) based on the Mask R-CNN model. AC R-CNN incorporates hybrid dilated convolution (HDC) and attention modules into the feature extraction backbone network to enhance the segmentation of adhesive mushroom caps and focus on the segmentation objects. Furthermore, the Mask Branch module is replaced with PointRend to improve the network’s segmentation accuracy at the edges of the mushroom caps. These modifications effectively solve the problems of the original algorithm’s inability to segment adhesive Agrocybe cylindracea caps and low accuracy in edge segmentation. The experimental results demonstrate that AC R-CNN outperforms the original Mask R-CNN in terms of segmentation performance. The average precision (AP) is improved by 12.1%, and the F1 score is improved by 13.7%. Additionally, AC R-CNN outperforms other networks such as Mask Scoring R-CNN and BlendMask. Therefore, the research findings of this study can meet the high-precision segmentation requirements of Agrocybe cylindracea caps and lay a theoretical foundation for the development of subsequent intelligent phenotyping devices and harvesting robots.
This study investigates head nods in natural dyadic German Sign Language (DGS) interaction, with the aim of finding whether head nods serving different functions vary in their phonetic ...characteristics. Earlier research on spoken and sign language interaction has revealed that head nods vary in the form of the movement. However, most claims about the phonetic properties of head nods have been based on manual annotation without reference to naturalistic text types and the head nods produced by the addressee have been largely ignored. There is a lack of detailed information about the phonetic properties of the addressee's head nods and their interaction with manual cues in DGS as well as in other sign languages, and the existence of a form-function relationship of head nods remains uncertain. We hypothesize that head nods functioning in the context of affirmation differ from those signaling feedback in their form and the co-occurrence with manual items. To test the hypothesis, we apply OpenPose, a computer vision toolkit, to extract head nod measurements from video recordings and examine head nods in terms of their duration, amplitude and velocity. We describe the basic phonetic properties of head nods in DGS and their interaction with manual items in naturalistic corpus data. Our results show that phonetic properties of affirmative nods differ from those of feedback nods. Feedback nods appear to be on average slower in production and smaller in amplitude than affirmation nods, and they are commonly produced without a co-occurring manual element. We attribute the variations in phonetic properties to the distinct roles these cues fulfill in turn-taking system. This research underlines the importance of non-manual cues in shaping the turn-taking system of sign languages, establishing the links between such research fields as sign language linguistics, conversational analysis, quantitative linguistics and computer vision.
PDF
