YOLO-plum: A high precision and real-time improved algorithm for plum recognition.
Ontology highlight
ABSTRACT:
SUBMITTER: Niu Y
PROVIDER: S-EPMC10374091 | biostudies-literature | 2023
REPOSITORIES: biostudies-literature
Publications
YOLO-plum: A high precision and real-time improved algorithm for plum recognition.
Niu Yupeng Y Lu Ming M Liang Xinyun X Wu Qianqian Q Mu Jiong J
PloS one 20230727 7
Real-time, rapid, accurate, and non-destructive batch testing of fruit growth state is crucial for improving economic benefits. However, for plums, environmental variability, multi-scale, occlusion, overlapping of leaves or fruits pose significant challenges to accurate and complete labeling using mainstream algorithms like YOLOv5. In this study, we established the first artificial dataset of plums and used deep learning to improve target detection. Our improved YOLOv5 algorithm achieved more ac ...[more]
Similar Datasets
Project description:Comprehensive and quantitative assessment of human physical activity in daily life is valuable for healthcare, especially for those who suffer from obesity and neurological disorders or are at high risk of dementia. Common wearable devices, e.g., smartwatches, are insufficient and inaccurate for monitoring highly dynamic limb movements and assessing human motion. Here, we report a new wearable leg movement monitoring system incorporating a custom-made motion sensor with machine learning algorithm to perceive human motion accurately and comprehensively during diverse walking and running actions. The system enables real-time multimodal perceptions of personal identity, motion state, locomotion speed, and energy expenditure for wearers. A general law of extracting real-time metabolic energy from leg movements is verified although individual gaits show differences. In addition, we propose a novel sensing configuration combining unilateral lower leg movement velocity with its angular rate to achieve high accuracy and good generalizability while simplifying the wearable system. Advanced performances in personal identification (accuracy of 98.7%) and motion-state recognition (accuracy of 93.7%) are demonstrated. The wearable system also exhibites high-precision real-time estimations of locomotion speed (error of 3.04% to 9.68%) and metabolic energy (error of 4.18% to 14.71%) for new subjects across various time-varying conditions. The wearable system allows reliable leg movement monitoring and quantitative assessment of bodily kinematic and kinetic behaviors during daily activities, as well as safe identity authentication by gait parameters, which would greatly facilitate smart life, personal healthcare, and rehabilitation training.
| S-EPMC11918258 | biostudies-literature
Project description:In the application of driverless technology, current traffic sign recognition methods are susceptible to the influence of ambient light interference, target size changes and complex backgrounds, resulting in reduced recognition accuracy. To address these challenges, this study introduces an optimisation algorithm called ETSR-YOLO, which is based on the YOLOv5s algorithm. First, this study improves the path aggregation network (PANet) of YOLOv5s to enhance multi-scale feature fusion by generating an additional high-resolution feature layer to improve the recognition of YOLOv5s for small-sized objects. Second, the study introduces two improved C3 modules that aim to suppress background noise interference and enhance the feature extraction capabilities of the network. Finally, the study uses the Wise-IoU (WIoU) function in the post-processing stage to improve the learning ability and robustness of the algorithm to different samples. The experimental results show that ETSR-YOLO improves mAP@0.5 by 6.6% on the Tsinghua-Tencent 100K (TT100K) dataset and by 1.9% on the CSUST Chinese Traffic Sign Detection Benchmark 2021 (CCTSDB2021) dataset. In the experiments conducted on the embedded computing platform, ETSR-YOLO demonstrates a short average inference time, thereby affirming its capability to deliver dependable traffic sign detection for intelligent vehicles operating in real-world traffic scenes. The source code and test results of the models used in this study are available at https://github.com/cbrook16/ETSR-YOLO.
| S-EPMC10721062 | biostudies-literature
Project description:When aerial cameras get aerial remote sensing images, the defocus will occur because of reasons such as air pressure, temperature and ground elevation changes, resulting in different image sharpness of continual aerial remote sensing images. Nowadays, the rapidly developing feature matching algorithm will rapidly reduce the registration rate between images with different image sharpness. Therefore, in order to enable aerial cameras to get image sharpness parameters according to the locations of aerial image feature points with inconsistent sharpness, this paper proposes a feature matching algorithm between aerial images with different sharpness by using DEM data and multiple constraints. In this paper, the feature matching range is extended according to the modified aerial imaging model and the nonlinear soft margin support vector machine. Then the relative moving speed and its variation of the feature points in the image are obtained by using the extended L-k optical flow, and finally the epipolar geometric constraint is introduced. To locate the feature points is obtained under multiple constraints, there is no need to calculate the feature point descriptors, and some mismatched point pairs are corrected, which improves the matching efficiency and precision. The experimental results show the feature matching precision of this algorithm is more than 90%, and the running time and matching precision can meet various application needs of aerial cameras.
| S-EPMC9484699 | biostudies-literature
Project description:Surface defect inspection methods have proven effective in addressing casting quality control tasks. However, traditional inspection methods often struggle to achieve high-precision detection of surface defects in castings with similar characteristics and minor scales. The study introduces DES-YOLO, a novel real-time method for detecting castings' surface defects. In the DES-YOLO model, we incorporate the DSC-Darknet backbone network and global attention mechanism (GAM) module to enhance the identification of defect target features. These additions are essential for overcoming the challenge posed by the high similarity among defect characteristics, such as shrinkage holes and slag holes, which can result in decreased detection accuracy. An enhanced pyramid pooling module is also introduced to improve feature representation for small defective parts through multi-layer pooling. We integrate Slim-Neck and SIoU bounding box regression loss functions for real-time detection in actual production scenarios. These functions reduce memory overhead and enable real-time detection of surface defects in castings. Experimental findings demonstrate that the DES-YOLO model achieves a mean average precision (mAP) of 92.6% on the CSD-DET dataset and a single-image inference speed of 3.9 milliseconds. The proposed method proves capable of swiftly and accurately accomplishing real-time detection of surface defects in castings.
| S-EPMC11419617 | biostudies-literature
Project description:COVID-19 global cases have climbed to more than 33 million, with over a million total deaths, as of September, 2020. Real-time massive SARS-CoV-2 whole genome sequencing is key to tracking chains of transmission and estimating the origin of disease outbreaks. Yet no methods have simultaneously achieved high precision, simple workflow, and low cost. We developed a high-precision, cost-efficient SARS-CoV-2 whole genome sequencing platform for COVID-19 genomic surveillance, CorvGenSurv (Coronavirus Genomic Surveillance). CorvGenSurv directly amplified viral RNA from COVID-19 patients' Nasopharyngeal/Oropharyngeal (NP/OP) swab specimens and sequenced the SARS-CoV-2 whole genome in three segments by long-read, high-throughput sequencing. Sequencing of the whole genome in three segments significantly reduced sequencing data waste, thereby preventing dropouts in genome coverage. We validated the precision of our pipeline by both control genomic RNA sequencing and Sanger sequencing. We produced near full-length whole genome sequences from individuals who were COVID-19 test positive during April to June 2020 in Los Angeles County, California, USA. These sequences were highly diverse in the G clade with nine novel amino acid mutations including NSP12-M755I and ORF8-V117F. With its readily adaptable design, CorvGenSurv grants wide access to genomic surveillance, permitting immediate public health response to sudden threats.
| S-EPMC8249533 | biostudies-literature
Project description:Cryo-correlative light and electron microscopy (CLEM) is a technique that uses the spatiotemporal cues from fluorescence light microscopy (FLM) to investigate the high-resolution ultrastructure of biological samples by cryo-electron microscopy (cryo-EM). Cryo-CLEM provides advantages for identifying and distinguishing fluorescently labeled proteins, macromolecular complexes, and organelles from the cellular environment. Challenges remain on how correlation workflows and software tools are implemented on different microscope platforms to support automated cryo-EM data acquisition. Here, we present CorRelator: an open-source desktop application that bridges between cryo-FLM and real-time cryo-EM/ET automated data collection. CorRelator implements a pixel-coordinate-to-stage-position transformation for flexible, high accuracy on-the-fly and post-acquisition correlation. CorRelator can be integrated into cryo-CLEM workflows and easily adapted to standard fluorescence and transmission electron microscope (TEM) system configurations. CorRelator was benchmarked under live-cell and cryogenic conditions using several FLM and TEM instruments, demonstrating that CorRelator reliably supports real-time, automated correlative cryo-EM/ET acquisition, through a combination of software-aided and interactive alignment. CorRelator is a cross-platform software package featuring an intuitive Graphical User Interface (GUI) that guides the user through the correlation process. CorRelator source code is available at: https://github.com/wright-cemrc-projects/corr.
| S-EPMC8601405 | biostudies-literature
Project description:Frequent occurrence and long-term existence of respiratory diseases such as COVID-19 and influenza require bus drivers to wear masks correctly during driving. To quickly detect whether the mask is worn correctly on resource-constrained devices, a lightweight target detection network SAI-YOLO is proposed. Based on YOLOv4-Tiny, the network incorporates the Inception V3 structure, replaces two CSPBlock modules with the RES-SEBlock modules to reduce the number of parameters and computational difficulty, and adds a convolutional block attention module and a squeeze-and-excitation module to extract key feature information. Moreover, a modified ReLU (M-ReLU) activation function is introduced to replace the original Leaky_ReLU function. The experimental results show that SAI-YOLO reduces the number of network parameters and calculation difficulty and improves the detection speed of the network while maintaining certain recognition accuracy. The mean average precision (mAP) for face-mask-wearing detection reaches 86% and the average precision (AP) for mask-wearing normative detection reaches 88%. In the resource-constrained device Raspberry Pi 4B, the average detection time after acceleration is 197 ms, which meets the actual application requirements.
| S-EPMC8592770 | biostudies-literature
Project description:ObjectivesTo evaluate a novel method for real-time tagged MRI with increased tag persistence using phase sensitive tagging (REALTAG), demonstrated for speech imaging.MethodsTagging is applied as a brief interruption to a continuous real-time spiral acquisition. REALTAG is implemented using a total tagging flip angle of 180° and a novel frame-by-frame phase sensitive reconstruction to remove smooth background phase while preserving the sign of the tag lines. Tag contrast-to-noise ratio of REALTAG and conventional tagging (total flip angle of 90°) is simulated and evaluated in vivo. The ability to extend tag persistence is tested during the production of vowel-to-vowel transitions by American English speakers.ResultsREALTAG resulted in a doubling of contrast-to-noise ratio at each time point and increased tag persistence by more than 1.9-fold. The tag persistence was 1150 ms with contrast-to-noise ratio >6 at 1.5T, providing 2 mm in-plane resolution, 179 frames/s, with 72.6 ms temporal window width, and phase sensitive reconstruction. The new imaging window is able to capture internal tongue deformation over word-to-word transitions in natural speech production.ConclusionTag persistence is substantially increased in intermittently tagged real-time MRI by using the improved REALTAG method. This makes it possible to capture longer motion patterns in the tongue, such as cross-word vowel-to-vowel transitions, and provides a powerful new window to study tongue biomechanics.
| S-EPMC7180094 | biostudies-literature
Project description:Farmers focus on reducing the cost of production and aim to increase profit. The objective of this study was to quantify the reduction of pesticides applied to soybean (Glycine max (L.) Merrill) and maize (Zea mays L.) crops in several stages of the production cycle using a site-specific spraying application based on real-time sensors in the Brazilian Cerrado region. The sprayers were equipped with a precision spraying control system based on a real-time sensor. The spraying operations were performed not only for herbicide, but also for fungicide and insecticides applications. The maps recorded the percentage of the spray boom when the application was turned on (on/off spray system) with nozzle-to-nozzle control. The precision spraying system based on real-time sensors reduced the volume of pesticides (including herbicides, insecticides, and fungicides) applied to soybean and maize crops. There was a more significant reduction in the volume of pesticides applied post-emergence of the crops in the initial stages of soybean and maize when the crops had less leaf area or less foliage coverage between the rows. The cost reduction achieved using this technology was 2.3 times lower than the cost associated with pesticide application over the entire area using a conventional sprayer. Under the experimental conditions, there were no differences in the average crop yield, compared to the historical productivity of soybean and maize crops by applying this technology because the recommended doses were not affected and the site of application was limited to points where the presence of plants was present was detected.
| S-EPMC8980047 | biostudies-literature
Project description:In order to improve the real-time and feasibility of traffic sign detection for autonomous driving in complex traffic environments, this paper proposes a small target detection algorithm for traffic signs based on the YOLOv8 model. First, the bottleneck of the C2f module in the original yolov8 network is replaced with the residual Faster-Block module in FasterNet, and then the new channel mixer convolution GLU (CGLU) in TransNeXt is combined with it to construct the C2f-faster-CGLU module, reducing the number of model parameters and computational load; Secondly, the SPPF module is combined with the large separable kernel attention (LSKA) to construct the SPPF-LSKA module, which greatly enhances the feature extraction ability of the model; Then, by adding a small target detection layer, the accuracy of small target detection such as traffic signs is greatly improved; Finally, the Inner-IoU and MPDIoU loss functions are integrated to construct WISE-Inner-MPDIoU, which replaces the original CIoU loss function, thereby improving the calculation accuracy. The model has been validated on two datasets Tsinghua-Tencent 100K (TT100K) and CSUST Chinese Traffic Sign Detection Benchmark 2021 (CCTSDB 2021), achieving Map50 of 89.8% and 98.9% respectively. The model achieves precision on par with existing mainstream algorithms, while being simpler, significantly reducing computational requirements, and being more suitable for small target detection tasks. The source code and test results of the models used in this study are available at https://github.com/lyzzzzyy/CSW-YOLO.git.
| S-EPMC11925293 | biostudies-literature