Search Results (8)

Lane detection is a key technology in automatic driving environment perception, and its accuracy directly affects vehicle positioning, path planning, and driving safety. In this study, an enhanced real-time model for lane detection based on an improved DeepLabV3+ architecture is proposed to address the challenges posed by complex dynamic backgrounds and blurred road boundaries in suburban road scenarios. To address the lack of feature correlation in the traditional Atrous Spatial Pyramid Pooling (ASPP) module of the DeepLabV3+ model, we propose an improved LC-DenseASPP module. First, inspired by DenseASPP, the number of dilated convolution layers is reduced from six to three by adopting a dense connection to enhance feature reuse, significantly reducing computational complexity. Second, the convolutional block attention module (CBAM) attention mechanism is embedded after the LC-DenseASPP dilated convolution operation. This effectively improves the model’s ability to focus on key features through the adaptive refinement of channel and spatial attention features. Finally, an image-pooling operation is introduced in the last layer of the LC-DenseASPP to further enhance the ability to capture global context information. DySample is introduced to replace bilinear upsampling in the decoder, ensuring model performance while reducing computational resource consumption. The experimental results show that the model achieves a good balance between segmentation accuracy and computational efficiency, with a mean intersection over union (mIoU) of 95.48% and an inference speed of 128 frames per second (FPS). Additionally, a new lane-detection dataset, SubLane, is constructed to fill the gap in the research field of lane detection in suburban road scenarios. Full article

This study aimed to investigate the differences in duration perception between athletes and non-athletes when looking at implied motion images within sub- and supra-second time ranges. By adopting the temporal bisection method, the study analyzed the duration perception of 20 college student athletes and 20 non-athletes regarding the implied motion of daily life (running and walking) and static postures (standing). The results showed that the effect of movement posture was significant, i.e., the perceived duration of the implied motion posture was longer than that of the static posture. Specifically, athletes perceived longer durations in the supra-second time range compared to non-athletes, indicating that long-term training enhanced athletes’ time perception abilities. The findings provide new insights into the cognitive mechanisms of time perception and emphasize the influence of long-term physical training on temporal perceptual capabilities. Full article

In recent years, deep convolutional neural network (CNN)-based image enhancement has shown outstanding performance. However, due to the problems of uneven illumination and low contrast existing in endoscopic images, the implementation of medical endoscopic image enhancement using CNN is still an exploratory and challenging task. An endoscopic image enhancement network (EIEN) based on the Retinex theory is proposed in this paper to solve these problems. The structure consists of three parts: decomposition network, illumination correction network, and reflection component enhancement algorithm. First, the decomposition network model of pre-trained Retinex-Net is retrained on the endoscopic image dataset, and then the images are decomposed into illumination and reflection components by this decomposition network. Second, the illumination components are corrected by the proposed self-attention guided multi-scale pyramid structure. The pyramid structure is used to capture the multi-scale information of the image. The self-attention mechanism is based on the imaging nature of the endoscopic image, and the inverse image of the illumination component is fused with the features of the green and blue channels of the image to be enhanced to generate a weight map that reassigns weights to the spatial dimension of the feature map, to avoid the loss of details in the process of multi-scale feature fusion and image reconstruction by the network. The reflection component enhancement is achieved by sub-channel stretching and weighted fusion, which is used to enhance the vascular information and image contrast. Finally, the enhanced illumination and reflection components are multiplied to obtain the reconstructed image. We compare the results of the proposed method with six other methods on a test set. The experimental results show that EIEN enhances the brightness and contrast of endoscopic images and highlights vascular and tissue information. At the same time, the method in this paper obtained the best results in terms of visual perception and objective evaluation. Full article

In the field of time psychology, the functional significance of the contingent negative variation (CNV) component in time perception and whether the processing mechanisms of sub- and supra-second are similar or different still remain unclear. In the present study, event-related potential (ERP) technology and classical temporal discrimination tasks were used to explore the neurodynamic patterns of sub- and supra-second time perception. In Experiment 1, the standard interval (SI) was fixed at 500 ms, and the comparison interval (CI) ranged from 200 ms to 800 ms. In Experiment 2, the SI was fixed at 2000 ms, and the CI ranged from 1400 ms to 2600 ms. Participants were required to judge whether the CI was longer or shorter than the SI. The ERP results showed similar CNV activity patterns in the two experiments. Specifically, CNV amplitude would be more negative when the CI was longer or closer to the memorized SI. CNV peak latency increased significantly until the CI reached the memorized SI. We propose that CNV amplitude might reflect the process of temporal comparison, and CNV peak latency might represent the process of temporal decision-making. To our knowledge, it is the first ERP task explicitly testing the two temporal scales, sub- and supra-second timing, in one study. Taken together, the present study reveals a similar functional significance of CNV between sub- and supra-second time perception. Full article

This study explored the experiences of healthcare consumers who had recently attempted suicide, and their carers, following placement on a Suicide Prevention Pathway based on the Zero Suicide framework. Qualitative interviews were conducted with 10 consumers and 5 carers using a semi-structured interview schedule. Interviews were transcribed and thematic analysis was applied to identify prominent themes and sub-themes. Three interrelated themes were identified. The first theme was ‘Feeling safe and valued’ with the associated sub-theme pertaining to perceived stigmatizing treatment and self-stigma. The second was ‘Intersection of consumer and staff/organizational needs’ with a related sub-theme of time pressure and reduced self-disclosure. The final theme was ‘Importance of the ‘whole picture’, highlighting the relevance of assessing and addressing psychosocial factors when planning for consumer recovery. Overall, consumers and their carers reported a favorable experience of the Suicide Prevention Pathway; however, there were several areas identified for improvement. These included reconciling the time-pressures of a busy health service system, ensuring consumers and carers feel their psychosocial concerns are addressed, and ensuring that adequate rapport is developed. Key to this is ensuring consumers feel cared for and reducing perceptions of stigma. Full article

The PHD (Probability Hypothesis Density) filter is a sub-optimal multi-target Bayesian filter based on a random finite set, which is widely used in the tracking and estimation of dynamic objects in outdoor environments. Compared with the outdoor environment, the indoor environment space and the shape of dynamic objects are relatively small, which puts forward higher requirements on the estimation accuracy and response speed of the filter. This paper proposes a method for fast and high-precision estimation of the dynamic objects’ velocity for mobile robots in an indoor environment. First, the indoor environment is represented as a dynamic grid map, and the state of dynamic objects is represented by its grid cells state as random finite sets. The estimation of dynamic objects’ speed information is realized by using the measurement-driven particle-based PHD filter. Second, we bound the dynamic grid map to the robot coordinate system and derived the update equation of the state of the particles with the movement of the robot. At the same time, in order to improve the perception accuracy and speed of the filter for dynamic targets, the CS (Current Statistical) motion model is added to the CV (Constant Velocity) motion model, and interactive resampling is performed to achieve the combination of the advantages of the two. Finally, in the Gazebo simulation environment based on ROS (Robot Operating System), the speed estimation and accuracy analysis of the square and cylindrical dynamic objects were carried out respectively when the robot was stationary and in motion. The results show that the proposed method has a great improvement in effect compared with the existing methods. Full article

Background: Pain after breast cancer surgery remains largely unexplained and inconsistently quantified. This study aims to describe the perioperative pain patterns in patients with breast cancer, up to two years after surgery. Methods: This is a pre-planned sub-study of the Ketorolac in Breast Cancer (KBC) trial. The KBC trial was a multicentre, prospective, double-blind, placebo-controlled, randomised trial of a single dose of 30 mg of ketorolac just before breast cancer surgery, aiming to test its effect on recurrences. This sub-study focuses only on pain outcomes. From 2013 to 2015, 203 patients were randomised to ketorolac (n = 96) or placebo (n = 107). Structured questionnaires were delivered by telephone after one and two years, exploring the presence, location, permanence, and frequency of pain. Patients’ perceptions of pain were captured by an open-ended question, the responses to which were coded and classified using hierarchical clustering. Results: There was no difference in pain between the ketorolac and the placebo group. The reported incidence of permanent pain was 67% and 45% at one and two years, respectively. The largest category was musculoskeletal pain. Permanent pain was mainly described in patients with musculoskeletal pain. The description of pain changed in most patients during the second postoperative year, i.e., moved from one category to another (no pain, permanent, or non-permanent pain, but also, the localisation). This phenomenon includes patients without pain at one year. Conclusions: Pain is a complex phenomenon, but also a fragile and unstable endpoint. Pain after breast cancer surgery does not necessarily mean breast pain but also musculoskeletal and other pains. The permanence of pain and the pain phenotype can change over time. Full article

Driven by technological advances and economic gain, society’s electronic systems are becoming larger, faster, more decentralized and autonomous, and yet with increasing global reach. A prime example are the networks of financial markets which—in contrast to popular perception—are largely all-electronic and decentralized with no top-down real-time controller. This prototypical system generates complex subsecond dynamics that emerge from a decentralized network comprising heterogeneous hardware and software components, communications links, and a diverse ecology of trading algorithms that operate and compete within this all-electronics environment. Indeed, these same technological and economic drivers are likely to generate a similarly competitive all-electronic ecology in a variety of future cyberphysical domains such as e-commerce, defense and the transportation system, including the likely appearance of large numbers of autonomous vehicles on the streets of many cities. Hence there is an urgent need to deepen our understanding of stability, safety and security across a wide range of ultrafast, large, decentralized all-electronic systems—in short, society will eventually need to understand what extreme behaviors can occur, why, and what might be the impact of both intentional and unintentional system perturbations. Here we set out a framework for addressing this issue, using a generic model of heterogeneous, adaptive, autonomous components where each has a realistic limit on the amount of information and processing power available to it. We focus on the specific impact of delayed information, possibly through an accidental shift in the latency of information transmission, or an intentional attack from the outside. While much remains to be done in terms of developing formal mathematical results for this system, our preliminary results indicate the type of impact that can occur and the structure of a mathematical theory which may eventually describe it. Full article