Tiny Targets Research Articles

Community empowerment through participation in a tsetse control project in the Democratic Republic of Congo.

Gambiense Human African Trypanosomiasis (g-HAT) is a neglected tropical disease caused by trypanosomes transmitted by tsetse flies. In 2017, a pilot community-based project was launched in three villages in DRC with the overall goal of empowering community members to control tsetse using Tiny Targets which attract and kill tsetse. In this paper, we assess the community participation process in these three pilot villages over >4 years and evaluate to what extent this resulted in the empowerment of communities. We conducted a qualitative study using a participatory research approach. Together with community members of the three pilot villages from the endemic Kwilu province, we evaluated changes in project participation, community empowerment and perception of future participation at three different time points (September 2017, September 2018 and November 2021) over a 4-year period using participatory workshops and focus group discussions (FGD). We used a thematic content approach to analyse both workshop notes and FGD transcripts. The community identified five indicators to evaluate participation: (1) Leadership & Ownership, (2) Organisation & Planning, (3) Willingness, (4) Autonomy and (5) Community Involvement. The participation experience described by community members was characterised by a rapid growth of empowerment in the first year and sustained high levels thereafter. Community participants were willing to engage in potential future projects and continue to be supported by their Tiny Target project partner. However, they identified an imbalance in the power relationship within the committee and with the Tiny Target partners that limit the extent of empowerment attained. The intervention had broader benefits of community empowerment but this was limited by perceptions of being part of wider "top down" programme and by stakeholders attitude toward community participation. If empowerment is to be an important objective of projects and programmes then the needs identified by communities must be recognised and attitude of sharing power encouraged.

SADENet: A supervised attention delicate enhanced network for subtle person detection

Object detection algorithms have been developed for decades, and one of remaining important challenges is the detection of subtle targets in complex environments. Many convolution neural network (CNN) based methods have been proposed to handle this problem. However, the information pertaining to subtle targets is delicate and can easily be lost or neglected in the upsampling and downsampling stages of conventional CNN. In this paper, we propose a new subtle target detection network, named the supervised attention delicate enhanced network (SADENet). Firstly, two sample vertebras are designed to solve the problem of information loss during upsampling and downsampling. Then, an enhanced context attention module (ECAM) is proposed, which extends the original supervised heatmap by fusing information from different scales. Based on the ECAM and the respective advantages of high-resolution and low-resolution feature maps, two effective sampling attention modules, the semantic fidelity upsampling module and the location enhancement downsampling module, are created to build a bi-directional connection neck structure. The effectiveness of our proposed method is demonstrated in experiments on the TinyPerson dataset, which outperforms many state-of-the-art detectors, especially in the detection of tiny and tiny1 scale targets.

Cotton Stubble Detection Based on Improved YOLOv3

The stubble after cotton harvesting was used as the detection object to achieve the visual navigation operation for residual film recovery after autumn. An improved (You Only Look Once v3) YOLOv3-based target detection algorithm was proposed to detect cotton stubble. First, field images of residual film recycling were collected. Considering the inconsistency between stubble size and shape, a segmented labeling data set of stubble is proposed. Secondly, the Darknet-53 backbone of the original YOLOv3 network is improved to accommodate tiny targets. Next, the prediction anchor box of the improved detection backbone is clustered using K-means++, and the size of the prediction anchor box suitable for improved YOLOv3 is determined. Finally, for the false detection points after detection, a mean value denoising method is used to remove the false detection points. Feature points are extracted from the denoised stubble, and the candidate points are fitted by the least square method to obtain the navigation line. The optimal model with a mean average precision (mAP) of 0.925 is selected for testing at the test stage. The test results show that the algorithm in this article can detect the stubble of residual film recovery images at different locations, different time periods, and different camera depression angles without misdetection. The detection speed of a single image is 98.6 ms. Based on an improvement over YOLOv3, the improved model has a significantly higher detection rate in different scenarios than YOLOv3. This can provide practical technical support for the visual navigation of residual film recovery.

Turkey Tiny Targets Report: Tobacco Advertisement, Sales, Product Displays, and Purchase Incentives around Primary, and Secondary Schools

Turkey Tiny Targets Report: Tobacco Advertisement, Sales, Product Displays, and Purchase Incentives around Primary, and Secondary Schools

FM-STDNet: High-Speed Detector for Fast-Moving Small Targets Based on Deep First-Order Network Architecture

Identifying objects of interest from digital vision signals is a core task of intelligent systems. However, fast and accurate identification of small moving targets in real-time has become a bottleneck in the field of target detection. In this paper, the problem of real-time detection of the fast-moving printed circuit board (PCB) tiny targets is investigated. This task is very challenging because PCB defects are usually small compared to the whole PCB board, and due to the pursuit of production efficiency, the actual production PCB moving speed is usually very fast, which puts higher requirements on the real-time of intelligent systems. To this end, a new model of FM-STDNet (Fast Moving Small Target Detection Network) is proposed based on the well-known deep learning detector YOLO (You Only Look Once) series model. First, based on the SPPNet (Spatial Pyramid Pooling Networks) network, a new SPPFCSP (Spatial Pyramid Pooling Fast Cross Stage Partial Network) spatial pyramid pooling module is designed to adapt to the extraction of different scale size features of different size input images, which helps retain the high semantic information of smaller features; then, the anchor-free mode is introduced to directly classify the regression prediction information and do the structural reparameterization construction to design a new high-speed prediction head RepHead to further improve the operation speed of the detector. The experimental results show that the proposed detector achieves 99.87% detection accuracy at the fastest speed compared to state-of-the-art depth detectors such as YOLOv3, Faster R-CNN, and TDD-Net in the fast-moving PCB surface defect detection task. The new model of FM-STDNet provides an effective reference for the fast-moving small target detection task.

GBH-YOLOv5: Ghost Convolution with BottleneckCSP and Tiny Target Prediction Head Incorporating YOLOv5 for PV Panel Defect Detection

Photovoltaic (PV) panel surface-defect detection technology is crucial for the PV industry to perform smart maintenance. Using computer vision technology to detect PV panel surface defects can ensure better accuracy while reducing the workload of traditional worker field inspections. However, multiple tiny defects on the PV panel surface and the high similarity between different defects make it challenging to accurately identify and detect such defects. This paper proposes an approach named Ghost convolution with BottleneckCSP and a tiny target prediction head incorporating YOLOv5 (GBH-YOLOv5) for PV panel defect detection. To ensure better accuracy on multiscale targets, the BottleneckCSP module is introduced to add a prediction head for tiny target detection to alleviate tiny defect misses, using Ghost convolution to improve the model inference speed and reduce the number of parameters. First, the original image is compressed and cropped to enlarge the defect size physically. Then, the processed images are input into GBH-YOLOv5, and the depth features are extracted through network processing based on Ghost convolution, the application of the BottleneckCSP module, and the prediction head of tiny targets. Finally, the extracted features are classified by a Feature Pyramid Network (FPN) and a Path Aggregation Network (PAN) structure. Meanwhile, we compare our method with state-of-the-art methods to verify the effectiveness of the proposed method. The proposed PV panel surface-defect detection network improves the mAP performance by at least 27.8%.

Driver distraction detection based on lightweight networks and tiny object detection.

Real-time and efficient driver distraction detection is of great importance for road traffic safety and assisted driving. The design of a real-time lightweight model is crucial for in-vehicle edge devices that have limited computational resources. However, most existing approaches focus on lighter and more efficient architectures, ignoring the cost of losing tiny target detection performance that comes with lightweighting. In this paper, we present MTNet, a lightweight detector for driver distraction detection scenarios. MTNet consists of a multidimensional adaptive feature extraction block, a lightweight feature fusion block and utilizes the IoU-NWD weighted loss function, all while considering the accuracy gain of tiny target detection. In the feature extraction component, a lightweight backbone network is employed in conjunction with four attention mechanisms strategically integrated across the kernel space. This approach enhances the performance limits of the lightweight network. The lightweight feature fusion module is designed to reduce computational complexity and memory access. The interaction of channel information is improved through the use of lightweight arithmetic techniques. Additionally, CFSM module and EPIEM module are employed to minimize redundant feature map computations and strike a better balance between model weights and accuracy. Finally, the IoU-NWD weighted loss function is formulated to enable more effective detection of tiny targets. We assess the performance of the proposed method on the LDDB benchmark. The experimental results demonstrate that our proposed method outperforms multiple advanced detection models.

A Simplified Dual-Weighted Three-Layer Window Local Contrast Method for Infrared Small-Target Detection

In the realm of infrared small-target detection, the weighted local contrast approaches, which seek to improve targets by the defined weighted factors, have garnered a lot of interest. However, there are several problems with these methods as follows. 1) The vast number of local contrast sliding sub-windows restricts the time efficiency. 2) The dim targets in the complicated backgrounds are incorrectly eliminated by the background suppression procedure. 3) The background noise in the complicated environment cannot be effectively muted. A simplified dual-weighted three-layer window local contrast method (SDWTLLCM) is suggested in this work as a solution to these issues. In order to extract tiny targets and suppress complicated backgrounds, a hierarchical convolution filtering window is first created. Then, even without sub-window division, a simple three-layer sliding window is created for time efficiency enhancement. The dual-weighted local contrast approach is also intended to minimize the background and further highlight tiny objects. Eventually, the tiny targets may be extracted more effectively using the adaptive threshold segmentation procedure. The vast experimental findings show that our suggested strategy is effective and efficient.

Multiscale attention-based detection of tiny targets in aerial beach images

Tiny target detection in marine scenes is of practical importance in marine vision applications such as personnel search and rescue, navigation safety, and marine management. In the past few years, methods based on deep convolutional neural networks (CNN) have performed well for targets of common sizes. However, the accurate detection of tiny targets in marine scene images is affected by three difficulties: perspective multiscale, tiny target pixel ratios, and complex backgrounds. We proposed the feature pyramid network model based on multiscale attention to address the problem of tiny target detection in aerial beach images with large field-of-view, which forms the basis for the tiny target recognition and counting. To improve the ability of the tiny targets’ feature extraction, the proposed model focuses on different scales of the images to the target regions based on the multiscale attention enhancement module. To improve the effectiveness of tiny targets’ feature fusion, the pyramid structure is guided by the feature fusion module in order to give further semantic information to the low-level feature maps and prevent the tiny targets from being overwhelmed by the information at the high-level. Experimental results show that the proposed model generally outperforms existing models, improves accuracy by 8.56 percent compared to the baseline model, and achieves significant performance gains on the TinyPerson dataset. The code is publicly available via Github.

Detection of residual feed in aquaculture using YOLO and Mask RCNN

A dual-strategy residual feed detection algorithm based on improved You Only Look Once (YOLO) v3 and Mask Region-Based Convolutional Networks (RCNN) was explored for detecting residual feed in aquaculture areas. After improving the YOLO v3 network structure, the program can better extract the boundary box of swimming crabs and recognize tiny targets. Using the customized Mask RCNN, the region proposal network (RPN) traversed the fixed-size prior frame for small targets, which reduced false negatives in the inference process and speeded up the network. Using the YOLO v3 output, which extracts image information for swimming crab, as the input for Mask RCNN, the RPN recommended region and the probability of background misidentification were further reduced, which made the improved network more rapid and accurate. The precision of the local rapid detection model was 84%, the real-time detection time was 0.05 s, the detection precision was 96.5%, and the recall rate was 97%. Thus, the dual-strategy detection algorithm for residual feed developed herein could accurately identify residual feed and effectively reduce feed waste.

Identification and Detection of Biological Information on Tiny Biological Targets Based on Subtle Differences

In order to detect different biological features and dynamic tiny targets with subtle features more accurately and efficiently and analyze the subtle differences of biological features, this paper proposes classifying and identifying the local contour edge images of biological features and different types of targets and reveals high similarities in their subtle features. Taking pigeons as objects, there is little difference in appearance between female pigeons and male pigeons. Traditional methods need to manually observe the morphology near the anus of pigeons to identify their sex or carry out chromosome examination or even molecular biological examination to achieve accurate sex identification. In this paper, a compound marker region for extracting gender features is proposed. This area has a strong correlation with the gender difference of pigeons, and its area’s proportion is low, which can reduce calculation costs. A dual-weight image fusion feature enhancement algorithm based on edge detection is proposed. After the color information and contour information of the image are extracted, a new feature enhancement image is fused according to a pair of weights, and the difference between tiny features increased so as to realize the detection and identification of pigeon sex by visual methods. The results show that the detection accuracy is 98%, and the F1 value is 0.98. Compared with the original data set without any enhancement, the accuracy increased by 32% and the F1 score increased by 0.35. Experiments show that this method can achieve accurate visual sex classifications of pigeons and provide intelligent decision data for pigeon breeding.

An improved cascade R-CNN and RGB-D camera-based method for dynamic cotton top bud recognition and localization in the field

Cotton top cutting is an indispensable part of cotton planting. Cotton top bud detection and localization are highly challenging tasks because of tiny targets, dense growth and varying illumination. To achieve the automatic cutting of cotton buds in the field, a cotton top bud recognition and location algorithm adapted to a moving platform in the field based on images acquired by a red, green, blue and depth (RGB-D) camera was developed. In this study, an improved Cascade R-CNN network was proposed to detect cotton top bud regions on RGB images, and three-dimensional (3D) coordinates of targets were obtained by combining color images and depth images from RGB-D cameras. The 3D spatial position of the target in the world coordinate system was affected by the time of the cotton top bud recognition algorithm, the forward speed of the mobile platform and the time consumption of the manipulator moving to the target position. A dynamic compensation method of target coordinates in the moving direction was proposed to ensure the identification and positioning accuracy of cotton top buds in the moving process. To verify the effectiveness of the proposed algorithm, cotton top bud recognition and localization experiments were conducted in the field. The average precision with the proposed improved Cascade R-CNN model was 97.5 %, and the FPS was 13.3 frames per second, which was suitable for different period of a day. The average error of the positioning accuracy in the platform forwarding direction was 4.2 mm, 6.6 mm and 9.6 mm at speeds of 0.1 m/s, 0.2 m/s and 0.3 m/s, respectively. All the results demonstrate that the proposed method could be used for robotic cotton top cutting.

Research on Tiny Target Detection Technology of Fabric Defects Based on Improved YOLO

Fabric quality plays a crucial role in modern textile industry processes. How to detect fabric defects quickly and effectively has become the main research goal of researchers. The You Only Look Once (YOLO) series of networks have maintained a dominant position in the field of target detection. However, detecting small-scale objects, such as tiny targets in fabric defects, is still a very challenging task for the YOLOv4 network. To address this challenge, this paper proposed an improved YOLOv4 target detection algorithm: using a combined data augmentation method to expand the dataset and improve the robustness of the algorithm, obtaining the anchors suitable for fabric defect detection by using the k-means algorithm to cluster the ground truth box of the dataset, adding a new prediction layer in yolo_head in order to have a better effect on tiny target detection, integrating a convolutional block attention module into the backbone feature extraction network, and innovatively replacing the CIOU loss function with the CEIOU loss function to achieve accurate classification and localization of defects. Experimental results show that compared with the original YOLOv4 algorithm, the detection accuracy of the improved YOLOv4 algorithm for tiny targets has been greatly increased, the AP value of tiny target detection has increased by 12%, and the overall mean average precision (mAP) has increased by 3%. The prediction results of the proposed algorithm can provide enterprises with more accurate defect positioning, reduce the defect rate of fabric products, and improve their economic effect.

Big Tobacco, Tiny Targets: Campaign success in passing a TAPS ban in Georgia and keys to campaign success

Big Tobacco, Tiny Targets: Campaign success in passing a TAPS ban in Georgia and keys to campaign success

Image Enhancement-Based Detection with Small Infrared Targets

Today, target detection has an indispensable application in various fields. Infrared small-target detection, as a branch of target detection, can improve the perception capability of autonomous systems, and it has good application prospects in infrared alarm, automatic driving and other fields. There are many well-established algorithms that perform well in infrared small-target detection. Nevertheless, the current algorithms cannot achieve the expected detection effect in complex environments, such as background clutter, noise inundation or very small targets. We have designed an image enhancement-based detection algorithm to solve both problems through detail enhancement and target expansion. This method first enhances the mutation information, detail and edge information of the image and then improves the contrast between the target edge and the adjacent pixels to make the target more prominent. The enhancement improves the robustness of detection with background clutter or noise-flooded scenes. Moreover, bicubic interpolation is used on the input image, and the target pixels are expanded with upsampling, which enhances the detection effectiveness for tiny targets. From the results of qualitative and quantitative experiments, the algorithm proposed in this paper outperforms the existing work on various evaluation indicators.

Scaling up of tsetse control to eliminate Gambian sleeping sickness in northern Uganda.

Tsetse flies (Glossina) transmit Trypanosoma brucei gambiense which causes Gambian human African trypanosomiasis (gHAT) in Central and West Africa. Several countries use Tiny Targets, comprising insecticide-treated panels of material which attract and kill tsetse, as part of their national programmes to eliminate gHAT. We studied how the scale and arrangement of target deployment affected the efficacy of control. Between 2012 and 2016, Tiny Targets were deployed biannually along the larger rivers of Arua, Maracha, Koboko and Yumbe districts in North West Uganda with the aim of reducing the abundance of tsetse to interrupt transmission. The extent of these deployments increased from ~250 km2 in 2012 to ~1600 km2 in 2015. The impact of Tiny Targets on tsetse populations was assessed by analysing catches of tsetse from a network of monitoring traps; sub-samples of captured tsetse were dissected to estimate their age and infection status. In addition, the condition of 780 targets (~195/district) was assessed for up to six months after deployment. In each district, mean daily catches of tsetse (G. fuscipes fuscipes) from monitoring traps declined significantly by >80% following the deployment of targets. The reduction was apparent for several kilometres on adjacent lengths of the same river but not in other rivers a kilometre or so away. Expansion of the operational area did not always produce higher levels of suppression or detectable change in the age structure or infection rates of the population, perhaps due to the failure to treat the smaller streams and/or invasion from adjacent untreated areas. The median effective life of a Tiny Target was 61 (41.8-80.2, 95% CI) days. Scaling-up of tsetse control reduced the population of tsetse by >80% across the intervention area. Even better control might be achievable by tackling invasion of flies from infested areas within and outside the current intervention area. This might involve deploying more targets, especially along smaller rivers, and extending the effective life of Tiny Targets.

Multi-Site and Multi-Scale Unbalanced Ship Detection Based on CenterNet

Object detection plays an essential role in the computer vision domain, especially the machine learning-based approach, which has developed rapidly in the past decades. However, the development of convolutional neural networks in the marine field is relatively slow, such as in ship classification and tracking. In this paper, ship detection is considered as a central point classification and regression task but discards the non-maximum suppression operation. We first improved the deep layer aggregation network to enhance the feature extraction capability of tiny targets, then reduced the number of parameters through the lightweight convolution module, and finally employed a unique activation function to enhance the nonlinearity of the model. By doing this, the improved network not only suits unbalanced sample ratios in classifying, but is more robust in scenarios where both the number and resolution of samples are unstable. Experimental results demonstrate that the proposed approach obtains outstanding performance and especially suits tiny object detection compared with current advanced methods. Furthermore, in contrast to the original CenterNet framework, the mAP of the proposed approach increased by 5.6%.

Environmental mutations in the Campo focus challenge elimination of sleeping sickness transmission in Cameroon.

Sleeping sickness is still prevalent in Campo, southern Cameroon, despite the efforts of World Health Organization and the National Control Programme in screening and treating cases. Reducing disease incidence still further may need the control of tsetse vectors. We update entomological and parasitological parameters necessary to guide tsetse control in Campo. Tsetse flies were trapped, their apparent densities were evaluated as the number of flies captured per trap per day and mapped using GIS tools. Polymerase chain reaction based methods were used to identify their trypanosome infection rates. Glossina palpalis palpalis was the dominant vector species representing 93.42% and 92.85% of flies captured respectively during the heavy and light dry seasons. This species presented high densities, that is, 3.87, 95% CI [3.84-3.91], and 2.51, 95% CI [2.49-2.53] flies/trap/day in the two seasons. Moreover, 16.79% (of 1054) and 20.23% (of 1132 flies) were found infected with at least 1 trypanosome species for the 2 seasons respectively, Trypanosoma congolense being the most prevalent species, and Trypanosoma. brucei gambiense identified in 4 samples. Tsetse flies are abundant in Campo and present high trypanosome infection rates. The detection of tsetse infected with human trypanosomes near the newly created palm grove show workers' exposition. Tsetse densities maps built will guide vector control with 'Tiny Targets'.

Modeling time delay, external noise and multiple malware infections in wireless sensor networks

The essentiality of wireless sensor networks (WSNs) in military and health applications cannot be overemphasized, and this has made these tiny sensors soft targets for malware attacks. However, with the ubiquity of single-group infection models, few researchers have studied the effects of many concurrent infection types on WSNs. Therefore, we proposed the differential Susceptible–Exposed (virus)–Exposed (worm)–Infectious (virus)–Infectious (worm)–Recovered–Susceptible with Vaccination (SE1E2I1I2RV) epidemic model in order to study the dynamics of malicious-code dissemination in WSNs. Using the multi-group model, which represents multiple infections due to worms and viruses, first, delay analyses were performed and, through the Routh-Hurwitz criteria, sufficient conditions for stability were established. Secondly, the SE1E2I1I2RV model was extended to incorporate external noise, thereby changing the deterministic nature of the original model and allowing stochastic analyses for random factors such as temperature, physical obstructions, etc. The role that delay plays in the model is shown when it surpasses the critical value, thus the system loses stability and allows the occurrence of a Hopf bifurcation. Finally, numerical simulations were performed using Matlab in order to account for theoretical analyses.

The cost of tsetse control using 'Tiny Targets' in the sleeping sickness endemic forest area of Bonon in Côte d'Ivoire: Implications for comparing costs across different settings.

BackgroundWork to control the gambiense form of human African trypanosomiasis (gHAT), or sleeping sickness, is now directed towards ending transmission of the parasite by 2030. In order to supplement gHAT case-finding and treatment, since 2011 tsetse control has been implemented using Tiny Targets in a number of gHAT foci. As this intervention is extended to new foci, it is vital to understand the costs involved. Costs have already been analysed for the foci of Arua in Uganda and Mandoul in Chad. This paper examines the costs of controlling Glossina palpalis palpalis in the focus of Bonon in Côte d’Ivoire from 2016 to 2017.Methodology/Principal findingsSome 2000 targets were placed throughout the main gHAT transmission area of 130 km2 at a density of 14.9 per km2. The average annual cost was USD 0.5 per person protected, USD 31.6 per target deployed of which 12% was the cost of the target itself, or USD 471.2 per km2 protected. Broken down by activity, 54% was for deployment and maintenance of targets, 34% for tsetse surveys/monitoring and 12% for sensitising populations.Conclusions/SignificanceThe cost of tsetse control per km2 of the gHAT focus protected in Bonon was more expensive than in Chad or Uganda, while the cost per km2 treated, that is the area where the targets were actually deployed, was cheaper. Per person protected, the Bonon cost fell between the two, with Uganda cheaper and Chad more expensive. In Bonon, targets were deployed throughout the protected area, because G. p. palpalis was present everywhere, whereas in Chad and Uganda G. fuscipes fuscipes was found only the riverine fringing vegetation. Thus, differences between gHAT foci, in terms of tsetse ecology and human geography, impact on the cost-effectiveness of tsetse control. It also demonstrates the need to take into account both the area treated and protected alongside other impact indicators, such as the cost per person protected.