Real-Time Detection and Instance Segmentation of Strawberry in Unstructured Environment

The real-time detection and instance segmentation of strawberries constitute fundamental components in the development of strawberry harvesting robots.Real-time identification of strawberries in an unstructured envi-ronment is a challenging task.Current instance segmentation algorithms for strawberries suffer from issues such as poor real-time performance and low accuracy.To this end,the present study proposes an Efficient YOLACT(E-YOLACT)algorithm for strawberry detection and segmentation based on the YOLACT framework.The key enhancements of the E-YOLACT encompass the development of a lightweight attention mechanism,pyramid squeeze shuffle attention(PSSA),for efficient feature extraction.Additionally,an attention-guided context-feature pyramid network(AC-FPN)is employed instead of FPN to optimize the architecture’s performance.Furthermore,a feature-enhanced model(FEM)is introduced to enhance the prediction head’s capabilities,while efficient fast non-maximum suppression(EF-NMS)is devised to improve non-maximum suppression.The experimental results demonstrate that the E-YOLACT achieves a Box-mAP and Mask-mAP of 77.9 and 76.6,respectively,on the custom dataset.Moreover,it exhibits an impressive category accuracy of 93.5%.Notably,the E-YOLACT also demonstrates a remarkable real-time detection capability with a speed of 34.8 FPS.The method proposed in this article presents an efficient approach for the vision system of a strawberry-picking robot.

Triple-Branch Asymmetric Network for Real-time Semantic Segmentation of Road Scenes

As the field of autonomous driving evolves, real-time semantic segmentation has become a crucial part of computer vision tasks. However, most existing methods use lightweight convolution to reduce the computational effort, resulting in lower accuracy. To address this problem, we construct TBANet, a network with an encoder-decoder structure for efficient feature extraction. In the encoder part, the TBA module is designed to extract details and the ETBA module is used to learn semantic representations in a high-dimensional space. In the decoder part, we design a combination of multiple upsampling methods to aggregate features with less computational overhead. We validate the efficiency of TBANet on the Cityscapes dataset. It achieves 75.1% mean Intersection over Union(mIoU) with only 2.07 million parameters and can reach 90.3 Frames Per Second(FPS).

FIR-YOLACT:Fusion of ICIoU and Res2Net for YOLACT on Real-Time Vehicle Instance Segmentation

Autonomous driving technology has made a lot of outstanding achievements with deep learning,and the vehicle detection and classification algorithm has become one of the critical technologies of autonomous driving systems.The vehicle instance segmentation can perform instance-level semantic parsing of vehicle information,which is more accurate and reliable than object detection.However,the existing instance segmentation algorithms still have the problems of poor mask prediction accuracy and low detection speed.Therefore,this paper proposes an advanced real-time instance segmentation model named FIR-YOLACT,which fuses the ICIoU(Improved Complete Intersection over Union)and Res2Net for the YOLACT algorithm.Specifically,the ICIoU function can effectively solve the degradation problem of the original CIoU loss function,and improve the training convergence speed and detection accuracy.The Res2Net module fused with the ECA(Efficient Channel Attention)Net is added to the model’s backbone network,which improves the multi-scale detection capability and mask prediction accuracy.Furthermore,the Cluster NMS(Non-Maximum Suppression)algorithm is introduced in the model’s bounding box regression to enhance the performance of detecting similarly occluded objects.The experimental results demonstrate the superiority of FIR-YOLACT to the based methods and the effectiveness of all components.The processing speed reaches 28 FPS,which meets the demands of real-time vehicle instance segmentation.

DuFNet:Dual Flow Network of Real-Time Semantic Segmentation for Unmanned Driving Application of Internet of Things

The application of unmanned driving in the Internet of Things is one of the concrete manifestations of the application of artificial intelligence technology.Image semantic segmentation can help the unmanned driving system by achieving road accessibility analysis.Semantic segmentation is also a challenging technology for image understanding and scene parsing.We focused on the challenging task of real-time semantic segmentation in this paper.In this paper,we proposed a novel fast architecture for real-time semantic segmentation named DuFNet.Starting from the existing work of Bilateral Segmentation Network(BiSeNet),DuFNet proposes a novel Semantic Information Flow(SIF)structure for context information and a novel Fringe Information Flow(FIF)structure for spatial information.We also proposed two kinds of SIF with cascaded and paralleled structures,respectively.The SIF encodes the input stage by stage in the ResNet18 backbone and provides context information for the feature fusionmodule.Features from previous stages usually contain rich low-level details but high-level semantics for later stages.Themultiple convolutions embed in Parallel SIF aggregate the corresponding features among different stages and generate a powerful global context representation with less computational cost.The FIF consists of a pooling layer and an upsampling operator followed by projection convolution layer.The concise component provides more spatial details for the network.Compared with BiSeNet,our work achieved faster speed and comparable performance with 72.34%mIoU accuracy and 78 FPS on Cityscapes Dataset based on the ResNet18 backbone.

Real-time accurate hand path tracking and joint trajectory planning for industrial robots(Ⅰ)

Previously, researchers raised the accuracy for a robot′s hand to track a specified path in Car-tesian space mainly through increasing the number of knots on the path and the number of the path′s segments, which results in the heavier online computational burden for the robot controller. Aiming at overcoming this drawback, the authors propose a new kind of real-time accurate hand path tracking and joint trajectory planning method. Through selecting some extra knots on the specified hand path by a certain rule and introducing a sinusoidal function to the joint displacement equation of each segment, this method can greatly raise the path tracking accuracy of robot′s hand and does not change the number of the path′s segments. It also does not increase markedly the computational burden of robot controller. The result of simulation indicates that this method is very effective, and has important value in increasing the application of industrial robots.

Real-time accurate hand path tracking and joint trajectory planning for industrial robots(Ⅱ)

Previously, researchers raised the accuracy for a robot′s hand to track a specified path in Cartesian space mainly through increasing the number of knots on the path and the segments of the path. But, this method resulted in the heavier on line computational burden for the robot controller. In this paper, aiming at this drawback, the authors propose a new kind of real time accurate hand path tracking and joint trajectory planning method for robots. Through selecting some extra knots on the specified hand path by a certain rule, which enables the number of knots on each segment to increase from two to four, and through introducing a sinusoidal function and a cosinoidal function to the joint displacement equation of each segment, this method can raise the path tracking accuracy of robot′s hand greatly but does not increase the computational burden of robot controller markedly.

Real-time estimation of the structural utilization level of segmental tunnel lining

Over the last decades,an expansion of the underground network has been taking place to cope with the increasing amount of moving people and freight.As a consequence,it is of vital importance to guarantee the full functionality of the tunnel network by means of preventive maintenance and the monitoring of the tunnel lining state over time.A new method has been developed for the real-time prediction of the utilization level in tunnel segmental linings based on input monitoring data.The new concept is founded on a framework,which encompasses an offline and an online stage.In the former,the generation of feedforward neural networks is accomplished by employing synthetically produced data.Finite element simulations of the lining structure are conducted to analyze the structural response under multiple loading conditions.The scenarios are generated by assuming ranges of variation of the model input parameters to account for the uncertainty due to the not fully determined in situ conditions.Input and target quantities are identified to better assess the structural utilization of the lining.The latter phase consists in the application of the methodological framework on input monitored data,which allows for a real-time prediction of the physical quantities deployed for the estimation of the lining utilization.The approach is validated on a full-scale test of segmental lining,where the predicted quantities are compared with the actual measurements.Finally,it is investigated the influence of artificial noise added to the training data on the overall prediction performances and the benefits along with the limits of the concept are set out.

A Fast Underwater Optical Image Segmentation Algorithm Based on a Histogram Weighted Fuzzy C-means Improved by PSO

The S/N of an underwater image is low and has a fuzzy edge.If using traditional methods to process it directly,the result is not satisfying.Though the traditional fuzzy C-means algorithm can sometimes divide the image into object and background,its time-consuming computation is often an obstacle.The mission of the vision system of an autonomous underwater vehicle (AUV) is to rapidly and exactly deal with the information about the object in a complex environment for the AUV to use the obtained result to execute the next task.So,by using the statistical characteristics of the gray image histogram,a fast and effective fuzzy C-means underwater image segmentation algorithm was presented.With the weighted histogram modifying the fuzzy membership,the above algorithm can not only cut down on a large amount of data processing and storage during the computation process compared with the traditional algorithm,so as to speed up the efficiency of the segmentation,but also improve the quality of underwater image segmentation.Finally,particle swarm optimization (PSO) described by the sine function was introduced to the algorithm mentioned above.It made up for the shortcomings that the FCM algorithm can not get the global optimal solution.Thus,on the one hand,it considers the global impact and achieves the local optimal solution,and on the other hand,further greatly increases the computing speed.Experimental results indicate that the novel algorithm can reach a better segmentation quality and the processing time of each image is reduced.They enhance efficiency and satisfy the requirements of a highly effective,real-time AUV.

Restoring force correction based on online discrete tangent stiffness estimation method for real-time hybrid simulation

In real-time hybrid simulation（RTHS）, it is difficult if not impossible to completely erase the error in restoring force due to actuator response delay using existing displacement-based compensation methods. This paper proposes a new force correction method based on online discrete tangent stiffness estimation（online DTSE） to provide accurate online estimation of the instantaneous stiffness of the physical substructure. Following the discrete curve parameter recognition theory, the online DTSE method estimates the instantaneous stiffness mainly through adaptively building a fuzzy segment with the latest measurements, constructing several strict bounding lines of the segment and calculating the slope of the strict bounding lines, which significantly improves the calculation efficiency and accuracy for the instantaneous stiffness estimation. The results of both computational simulation and real-time hybrid simulation show that：（1） the online DTSE method has high calculation efficiency, of which the relatively short computation time will not interrupt RTHS; and（2） the online DTSE method provides better estimation for the instantaneous stiffness, compared with other existing estimation methods. Due to the quick and accurate estimation of instantaneous stiffness, the online DTSE method therefore provides a promising technique to correct restoring forces in RTHS.

Resource Efficient Hardware Implementation for Real-Time Traffic Sign Recognition

Traffic sign recognition (TSR, or Road Sign Recognition, RSR) is one of the Advanced Driver Assistance System (ADAS) devices in modern cars. To concern the most important issues, which are real-time and resource efficiency, we propose a high efficiency hardware implementation for TSR. We divide the TSR procedure into two stages, detection and recognition. In the detection stage, under the assumption that most German traffic signs have red or blue colors with circle, triangle or rectangle shapes, we use Normalized RGB color transform and Single-Pass Connected Component Labeling (CCL) to find the potential traffic signs efficiently. For Single-Pass CCL, our contribution is to eliminate the “merge-stack” operations by recording connected relations of region in the scan phase and updating the labels in the iterating phase. In the recognition stage, the Histogram of Oriented Gradient (HOG) is used to generate the descriptor of the signs, and we classify the signs with Support Vector Machine (SVM). In the HOG module, we analyze the required minimum bits under different recognition rate. The proposed method achieves 96.61% detection rate and 90.85% recognition rate while testing with the GTSDB dataset. Our hardware implementation reduces the storage of CCL and simplifies the HOG computation. Main CCL storage size is reduced by 20% comparing to the most advanced design under typical condition. By using TSMC 90 nm technology, the proposed design operates at 105 MHz clock rate and processes in 135 fps with the image size of 1360 × 800. The chip size is about 1 mm2 and the power consumption is close to 8 mW. Therefore, this work is resource efficient and achieves real-time requirement.

一种精确分段补偿的带隙基准电压源设计

针对传统的带隙基准电压的温漂系数较高的问题,设计了一种低温漂系数的带隙基准电压源。分别引入正负温度系数电流在高温和低温阶段对带隙基准电压进行线性补偿。NPN管作为开关管,通过工作在线性区的NMOS管作为等效电阻将正负温度系数电流转换成基极电压,控制NPN管导通和截止,进而控制开始和结束补偿的温度,实现精确补偿。基于SMIC 0.18μm工艺通过Cadence进行仿真。仿真结果为:在输入电压5 V时,温度在-40~125℃内,输出电压经过精确补偿后,温漂系数从16.48×10^(-6)/℃下降到0.829×10^(-6)/℃。输出基准电压最大仅变化152μV。在室温下,低频时电源抑制比为73.7 dB,电压源可以在2.8~7.5 V稳定工作。

人体图像精细化解析方法在语义边缘的性能评测与分析

人体图像精细化解析旨在为输入的人体图像进行像素级分类,属于细粒度的图像语义分割任务,由于具有广阔的应用场景,在近10年受到了研究者的关注,相关技术得以迅速发展.本文重点研究现有人体图像解析精细化模型对人体图像语义边缘的预测性能.首先,总结现有人体图像数据集,对比数据集在规模和标注类别方面的差异;其次,根据模型原理性差异,从通用图像语义分割、辅助信息引导、高分辨率特征增益和标签降噪4个方面对现有人体解析方法进行梳理和分类;再次,针对现有评估指标对于语义边缘区域预测能力敏感度不足的问题,构建新的评估指标,即平均边缘交并比(mean Boundary Intersection over Union,mBIoU),并用于对现有模型的评估,从数值上对比各方法的性能差异;最后,展望了人体解析未来的发展方向.研究结果表明:平均边缘交并比相较于现有指标能够更好地区分模型在语义边缘区域预测性能的差异,对人体图像精细化解析模型解决人体解析任务特有挑战的能力具有良好的评估作用,有利于未来算法的开发与性能评估.

基于多算法融合的破损陶瓷绝缘子图像识别与检测方法

为了提高输电线路安全稳定运行,在传统检测绝缘子缺陷的基础上,提出一种多算法融合的破损陶瓷绝缘子检测方法。基于FASTER-RCNN算法,将拍摄到的绝缘子图像进行训练,得到绝缘子串具体位置,并改进SBGFRLS(线性自适应滤波)算法,实现对瓷绝缘子破损的精确识别。首先利用FASTER-RCNN算法,选择Faster R-CNN网格作为检测器,识别出利用无人机拍摄得到的图像中的绝缘子串所在位置;然后,利用SVM(支持向量机)算法对绝缘子图像进行粗分割,得到粗分割后的绝缘子缺陷识别图,再在粗分割的基础上,运用改进的SBGFRLS算法对图像中的绝缘子进行精确识别,得到破损绝缘子定位图。实验结果表明,得到的绝缘子破损识别图可以验证该改进算法的可行性和有效性。

An improved pulse coupled neural networks model for semantic IoT

In recent years,the Internet of Things(IoT)has gradually developed applications such as collecting sensory data and building intelligent services,which has led to an explosion in mobile data traffic.Meanwhile,with the rapid development of artificial intelligence,semantic communication has attracted great attention as a new communication paradigm.However,for IoT devices,however,processing image information efficiently in real time is an essential task for the rapid transmission of semantic information.With the increase of model parameters in deep learning methods,the model inference time in sensor devices continues to increase.In contrast,the Pulse Coupled Neural Network(PCNN)has fewer parameters,making it more suitable for processing real-time scene tasks such as image segmentation,which lays the foundation for real-time,effective,and accurate image transmission.However,the parameters of PCNN are determined by trial and error,which limits its application.To overcome this limitation,an Improved Pulse Coupled Neural Networks(IPCNN)model is proposed in this work.The IPCNN constructs the connection between the static properties of the input image and the dynamic properties of the neurons,and all its parameters are set adaptively,which avoids the inconvenience of manual setting in traditional methods and improves the adaptability of parameters to different types of images.Experimental segmentation results demonstrate the validity and efficiency of the proposed self-adaptive parameter setting method of IPCNN on the gray images and natural images from the Matlab and Berkeley Segmentation Datasets.The IPCNN method achieves a better segmentation result without training,providing a new solution for the real-time transmission of image semantic information.

基于病种细分与精准预约的门诊服务优化研究与实践

目的打破原有传统单一粗放式预约模式,建立基于病种细分的精准预约,帮助患者精准匹配到合适的医生,让群众“看好病”。方法建立统一号源管理外联平台,引入号源细分、病种预分、多层诊疗、云端多学科联合会诊等全新概念,实现全新预约方式。结果新预约方式将号源资源进行分类、分层管理,平均退号率为19.55%、平均预约取消率为3.56%,低于传统预约方式同期值,人均门诊耗时1.62小时,低于上年度值,领衔专家平均转诊率20%,实现了号源细分、错峰就诊,避免了医疗服务资源的浪费。结论基于病种细分与精准预约挂号的门诊服务优化,通过按病种细分的预约管理,全方位满足不同病种患者的个性化诊疗需求,可以促进分级诊疗的进一步发展。

超声引导下肝切除术、精准区段肝蒂肝切除术对肝胆管结石患者机体炎症反应的影响

目的对比超声引导下肝切除术、精准区段肝蒂肝切除术治疗肝胆管结石(HC)患者的效果及对患者机体炎症反应的影响。方法回顾性收集2021年1月至2023年6月郑州大学附属郑州中心医院90例HC患者的病例资料,按手术方案不同分两组。以接受精准区段肝蒂肝切除术治疗的45例患者列为A组,以接受超声引导下肝切除术治疗的45例患者列为B组。对比两组围手术期指标、术前、术后14 d肝功能指标[碱性磷酸酶(ALP)、谷丙转氨酶(ALT)、总胆红素(TBIL)、谷草转氨酶(AST)]、免疫功能指标(CD3^(+)、CD4^(+)、CD4^(+)/CD8^(+))、炎症指标[白三烯B4(LTB4)、肿瘤坏死因子-α(TNF-α)、白介素-6(IL-6)]水平、结石残留率、并发症发生率。结果A组术后肝断面引流量、术中失血量相较于B组更低(P<0.05),两组排气时间、手术用时相比差异无统计意义(P>0.05);A组术后14 d血清ALP、ALT、TBIL、AST水平相较于B组更低(P<0.05);A组术后14 d CD3^(+)、CD4^(+)、CD4^(+)/CD8^(+)水平相较于B组更高(P<0.05);A组术后14 d血清LTB4、TNF-α、IL-6水平相较于B组更低(P<0.05);A组结石残留率、并发症总发生率6.67%(3/45)、4.44%(2/45)相较于B组28.89%(13/45)、22.22%(10/45)更低(P<0.05)。结论相较于超声引导下肝切除术治疗,通过精准区段肝蒂肝切除术治疗不仅能进一步降低术后肝断面引流量、术中失血量,缓解机体炎症反应,提升免疫功能,改善肝功能,同时还可进一步降低结石残留率及并发症发生率。

SPSSNet: a real-time network for image semantic segmentation

Although deep neural networks(DNNs)have achieved great success in semantic segmentation tasks,it is still challenging for real-time applications.A large number of feature channels,parameters,and floating-point operations make the network sluggish and computationally heavy,which is not desirable for real-time tasks such as robotics and autonomous driving.Most approaches,however,usually sacrifice spatial resolution to achieve inference speed in real time,resulting in poor performance.In this paper,we propose a light-weight stage-pooling semantic segmentation network(SPSSN),which can efficiently reuse the paramount features from early layers at multiple stages,at different spatial resolutions.SPSSN takes input of full resolution 2048×1024 pixels,uses only 1.42×10~6 parameters,yields 69.4%m Io U accuracy without pre-training,and obtains an inference speed of 59 frames/s on the Cityscapes dataset.SPSSN can run directly on mobile devices in real time,due to its light-weight architecture.To demonstrate the effectiveness of the proposed network,we compare our results with those of state-of-the-art networks.

基于深度语义的三阶段式问题检索模型

随着检索式问答技术的日趋成熟,如何有效利用现有的模型和检索工具,达到问答系统的整体优化,是亟待研究的现实问题.提出了一种基于深度语义的三阶段式问题检索模型(TSFR-RM),用于构筑智能客服问答系统.首先基于深度学习方法计算用户问题和知识库问题的文本表征相似度,锁定top-k候选答案集,同时赋予模型泛化检索的能力;其次针对用户问题与知识库问题答案对,构造多角度语义特征,进行精确比对计算;最后构造状态预测模型返回问题检索精准答案.通过真实文旅机构客服问答数据集实验及实际应用效果表明,该模型相较于其他基于特征和表征的问题检索模型,在精确率(precision)性能指标上最高提升9.3个百分点,提升优化了智能客服检索系统的准确性.

Lightweight Network Ensemble Architecture for Environmental Perception on the Autonomous System

It is important for the autonomous system to understand environmental information.For the autonomous system,it is desirable to have a strong generalization ability to deal with different complex environmental information,as well as have high accuracy and quick inference speed.Network ensemble architecture is a good choice to improve network performance.However,it is unsuitable for real-time applications on the autonomous system.To tackle this problem,a new neural network ensemble named partial-shared ensemble network(PSENet)is presented.PSENet changes network ensemble architecture from parallel architecture to scatter architecture and merges multiple component networks together to accelerate the inference speed.To make component networks independent of each other,a training method is designed to train the network ensemble architecture.Experiments on Camvid and CIFAR-10 reveal that PSENet achieves quick inference speed while maintaining the ability of ensemble learning.In the real world,PSENet is deployed on the unmanned system and deals with vision tasks such as semantic segmentation and environmental prediction in different fields.

Research on Automatic Elimination of Laptop Computer in Security CT Images Based on Projection Algorithm and YOLOv7-Seg

In civil aviation security screening, laptops, with their intricate structural composition, provide the potential for criminals to conceal dangerous items. Presently, the security process necessitates passengers to individually present their laptops for inspection. The paper introduced a method for laptop removal. By combining projection algorithms with the YOLOv7-Seg model, a laptop’s three views were generated through projection, and instance segmentation of these views was achieved using YOLOv7-Seg. The resulting 2D masks from instance segmentation at different angles were employed to reconstruct a 3D mask through angle restoration. Ultimately, the intersection of this 3D mask with the original 3D data enabled the successful extraction of the laptop’s 3D information. Experimental results demonstrated that the fusion of projection and instance segmentation facilitated the automatic removal of laptops from CT data. Moreover, higher instance segmentation model accuracy leads to more precise removal outcomes. By implementing the laptop removal functionality, the civil aviation security screening process becomes more efficient and convenient. Passengers will no longer be required to individually handle their laptops, effectively enhancing the efficiency and accuracy of security screening.