Search

The Visual Computer is a pioneering journal in the field of visual computational methods and applications. Since its founding in 1985, it has expanded its topics to include computer vision for graphics and AI for graphics. In 2023, the journal received over 2100 submissions and published 445 articles across 12 issues, totaling 6772 pages. The impact factor of the journal has increased to 3.5. The editorial board has undergone changes, with some associate editors leaving and new ones joining. The journal has also published special issues featuring the best papers from conferences such as CGI 2023 and Cyberworlds 2022. The CGI 2023 Visual Computer Best Paper Award was given to a paper on clinical assessment and pre-operative planning in virtual reality, while the second best paper award went to a paper on digital wallchart image super-resolution. The journal expresses gratitude to the individuals who support its publication, including the senior editor, editorial assistant, project coordinator, and staff at Springer. The Visual Computer looks forward to an exciting year in 2024 and encourages authors to submit their work. The call for papers for CGI 2024 is now open. [Extracted from the article]

Logistics parcel detection technology is critical for unmanned sorting. YOLOv5, the state-of-the-art (SOTA) object detection model, is a classic network widely used in engineering. However, on the premise of fast and accurate detection of logistics parcels, it confronts certain challenges of high computing load and parameter quantity. To address these issues, this paper proposes a two-scale lightweight deep learning model named SFYOLOv5. In this article, a lightweight feature extraction module called Pruned-Shuffle-Block (PSB) is proposed. Meanwhile, a double-layer pyramid structure for the medium and large target detection is created in accordance with the image size distribution of logistics parcels. With this structure, the Floating Point of Operations (FLOPs) and parameters in feature extraction were significantly reduced. In addition, a down sampling module named Focus for Downsampling (FFD) is designed and attention modules are introduced to extract high-level semantic information in logistics parcels. These modules not only compensate for the loss caused by down sampling but also improve the mean Average Precision (mAP). Finally, the comparison experiment is performed by using the self-built logistics parcel dataset. The results show that the mAP of the model reaches 99.1%, the number of model parameters decreased by 92.14%, and the FLOPs decreased by 89.57% compared with the existing SOTA model. This model can be used in logistics parcel intelligent sorting. [ABSTRACT FROM AUTHOR]

Person re-identification, as an essential research direction in intelligent security, has gained the focus of researchers and scholars. In practical scenarios, visible light cameras depend highly on lighting conditions and have limited detection capability in poor light. Therefore, many scholars have gradually shifted their research goals to cross-modality person re-identification. However, there are few relevant studies, and challenges remain in resolving the differences in the images of different modalities. In order to solve these problems, this paper will use the research method based on the attention mechanism to narrow the difference between the two modes and guide the network in a more appropriate direction to improve the recognition performance of the network. Aiming at the problem of using the attention mechanism method can improve training efficiency. However, it is easy to cause the model training instability. This paper proposes a cross-modal pedestrian re-recognition method based on the attention mechanism. A new attention mechanism module is designed to allow the network to use less time to focus on more critical features of a person. In addition, a cross-modality hard center triplet loss is designed to supervise the model training better. The paper has conducted extensive experiments on the above two methods on two publicly available datasets, which obtained better performance than similar current methods and verified the effectiveness and feasibility of the proposed methods in this paper. [ABSTRACT FROM AUTHOR]

Fruit recognition and location are the premises of robot automatic picking. YOLOv3 has been used to detect different fruits in complex environment. However, for the object with definite features, the complex network structure will increase the computing time and may cause overfitting. Therefore, this paper has carried out a lightweight design for the YOLOv3. This paper proposed an improved T-Net to detect tomato images. Firstly, the T-Net reduces the residual network layers. This paper changed the number of cycles in each group of the residual unit to 1, 2, 2, 1, and 1. Second, two feature layers with different scales are selected according to the features of tomatoes. Meanwhile, the convolutional layer at the neck has been reduced by two layers. Finally, the location and approximate diameter of the ripe tomato are obtained by combining the node information of the Intel D435i camera and T-Net in the Robot Operation System. T-Net obtains mean average precision (mAP) of 99.2%, F1-score of 98.9%, precision of 99.0%, and recall of 98.8% at a detection rate of 104.2 FPS. The proposed T-Net has outperformed the YOLOv3 with 0.4%, 0.1%, and 0.2% increase in precision, mAP, and F1-score. The detection speed of T-Net is 1.8 times faster than YOLOv3. The mean errors of the center coordinates and diameter of the tomato are 8.5 mm and 2.5 mm, respectively. This model provides a method for efficient real-time detection and location of tomatoes. [ABSTRACT FROM AUTHOR]

Manufacturing industry often uses 3D scanning technologies to inspect their products. Some of these techniques produce a point cloud that represent a section of the manufactured product. The clouds must be aligned to the model of the product in order to check its quality. Current registration methods are usually affected by dimensional problems or volumetric anomalies. This paper proposes a new method for the registration process aligning the cloud to the model in several steps. The first step is the state-of-the-art method. The second step uses the information acquired in the first one to perform a fine registration in order to not being affected by dimensional defects or little miss alignments in the previous step providing a huge improvement in the measurement of surface defects. In this paper, several techniques are proposed in order to provide a set of tools that the final users can tune to fit their needs. The whole procedure of registration can be run in real-time conditions using the sampling and caching strategies proposed. The methods proposed are tested over more than 10,000 profiles of a rail proving they successfully align the cloud and the model providing better results in the measurement of surface defects. [ABSTRACT FROM AUTHOR]

Nowadays, salient object detection methods based on deep learning have become a research focus. Therefore, how to reveal the representation mechanism and association rules of features at different levels and scales in order to improve the accuracy of salient object detection is a key issue to be solved. This paper proposes a salient object detection method to boost multi-scale information on multi-level aggregated features, which can accurately and flexibly aggregate multi-scale feature information via effective multi-level feature utilization. First, a scalable feature pyramid module is proposed, which can aggregate deep feature information in shallow features, thus obtaining aggregated features between different levels. Then, the global information enhancement module is built in the bottom-up network path to make up for the lost or weakened feature information in the process of multi-scale integration feature transmission. Next, internally convolve each level of aggregated feature via self-interactive module to enrich multi-scale information and improve the multi-scale representation ability of aggregated features. Finally, the global associativity loss function is designed to solve the noise caused by multi-scale variation so as to optimize the network training process, which effectively compensates for the deficiency of cross-entropy in the salient object detection task. The experimental results on four public datasets show that the performance of the proposed method has improved in contrast to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The traditional local binary pattern (LBP) is susceptible to the influence of the centre pixel and noise and cannot accurately identify wire rope surface defects. To solve this problem, an image segmentation-based central multiscale local binary pattern (ISCM-LBP) and grey level cooccurrence matrix (GLCM) feature fusion method is proposed in this paper for defect recognition. Image segmentation and multiple scales are introduced into the local binary pattern algorithm to improve the image detail description and suppress noise sensitivity. Second, the centre pixel is connected with the neighbourhood pixel to enhance the robustness of the centre pixel. To further improve the image integrity description, PCA dimensionality reduction and GLCM feature fusion are performed on the features extracted by the ISCM-LBP algorithm, and the steel wire rope surface defects are identified by a support vector machine classifier. Experimental results show that the overall recognition rate reaches 97.5%, which is at least 5% higher than that of other algorithms and can effectively identify various defects on the surface of wire rope. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks can effectively improve the performance of single-image super-resolution reconstruction. Deep networks tend to achieve better performance than others. However, the deep CNNs will lead to a dramatic increase in the size of parameters, limiting its application on embedding and resource-constrained devices, such as smart phone. To address the common problems of blurred image edges, inflexible convolution kernel size selection and slow convergence during training procedure due to redundant network structure in image super-resolution algorithms, this paper proposes a lightweight single-image super-resolution network that fuses multi-level features. The components are mainly two-level nested residual blocks. To better extract features and reduce the number of parameters, each residual block adopts an asymmetric structure. Firstly, it expands twice and then compresses the number of channels twice. Secondly, in the residual block, the feature information of different channels is weighted and fused by adding an autocorrelation weight unit. The quality of the reconstructed image of the proposed method is superior to the existing image super-resolution reconstruction methods in both subjective perception and objective evaluation indicators, and the reconstruction performance is better when the factor is large. [ABSTRACT FROM AUTHOR]

The paper presents a novel approach to developing an embodied conversation agent (ECA) that is capable of displaying empathy toward its human partner during interactions. The virtual agents are equipped with both memory and empathy capabilities, with the main focus being on modeling an empathy model associated with the ECA's memory. The paper presents the proposed model of empathy, as well as its connection with memory, and evaluates how this relationship affects the user's experience (UX) through experiments with volunteers who participated in long and short-term interactions. The results of the experiments show that the association of memory with the empathy model makes interactions with embodied conversational agents more enjoyable and to the user. This suggests that the ECA's ability to display empathy can have a positive impact on the user's experience, which is an important factor to consider when designing conversational agents for various purposes. Overall, the paper presents an interesting and valuable contribution to the field of embodied conversational agents and human–computer interaction. The incorporation of empathy and memory capabilities into an ECA has the potential to improve the user's experience and make interactions with machines more human-like. [ABSTRACT FROM AUTHOR]

To study the fruit image fusion technology in the case of thermal infrared and visible heterogeneous sources and the method of online defect detection on fruit fusion images, this paper takes apple as the research object and proposes a registration algorithm for thermal infrared and visible images of apple based on the registration of feature points with an active contour model. First, by designing a thermal infrared and visible image acquisition system, thermal infrared and visible images of apple in the same scene are obtained simultaneously. Then, the improved Chan-vese model is adopted to obtain the active contour segmentation curves of the thermal infrared and visible images of apple respectively. Next, the average Euclidean distance of all adjacent edge points on the active contour segmentation curve is calculated, and the alignment feature point set is constructed by the linear interpolation method based on the obtained average distance, and the optimal scale transformation factor and the optimal horizontal transformation factor are obtained by calculating the partial Hausdorff distance between the two feature point sets. Finally, the registered visible image is acquired based on the obtained affine transformation matrix, thus realizing the registration of the thermal infrared and visible images of apple. The experimental results on the self-built image dataset indicate that the algorithm proposed in this paper can accurately match the heterogeneous images of intact fruit, calyx/stems, and defective fruit, and it performs excellently in terms of precise matching rate and root mean square error, and the high alignment success rate of 96%. Also, it has much better performance than other methods. The proposed registration algorithm can accurately match thermal infrared and visible images of apple, and lays the foundation for further research on the image fusion of thermal infrared and visible, apple surface defect detection, as well as the construction of online dual-light apple grading systems. [ABSTRACT FROM AUTHOR]