The research team, led by Zhi Qiu and colleagues, built their system around YOLO11, a single-stage object detection architecture released by Ultralytics in September 2024. Single-stage detectors such as the YOLO family and SSD perform end-to-end inference in a single pass, making them far faster than two-stage models like the R-CNN series, which achieve excellent accuracy but cannot keep up with real-time sorting lines or field robots. YOLO11 follows the classic four-module design of input, backbone, neck, and head, and introduces refinements such as the C3k2 residual convolution block for efficient gradient flow and the C2PSA spatial attention module, which helps the network focus on informative regions under occlusion, cluttered backgrounds, and small targets. Of the five available sizes, the authors selected the mid-small YOLO11s variant as their baseline, judging its balance of accuracy and speed best suited to orchard conditions.

Before any architecture work could begin, the team needed data that reflected the messy reality of a working plantation. They collected 2,092 images in natural orchard environments and supplemented them with 3,000 public images from the Roboflow platform, yielding 5,092 valid samples. The shooting conditions were deliberately harsh and varied: sunny and overcast skies, early morning and dusk light, midday overexposure, evening underexposure, handheld vibration, rain-blurred lenses, branch occlusion, fruit overlap, clustered and solitary fruits, and both close-range and distant views. Each fruit was labeled as raw, meaning predominantly light green or in a red-green color-turning stage, or ripe, meaning predominantly bright red and meeting harvest criteria. Ambiguous samples, fruits more than 90 percent hidden, color-similar interfering objects, and flower buds were excluded from annotation. After size unification, denoising, and contrast equalization, the dataset was split 7:2:1 into 3,565 training, 1,019 validation, and 508 test images.

With the baseline established, the researchers attacked the problem along four fronts. The first was the detection head. Standard YOLO11 uses a two-branch decoupled head in which classification and confidence prediction share a pathway while only bounding box regression runs independently. The team designed a TripleDetect head that splits all three subtasks, localization, classification, and confidence, into fully independent parallel branches, eliminating feature competition and gradient conflict between heterogeneous objectives. To keep the head light, the conventional 3-by-3 convolutions in the regression branch were replaced with depthwise separable convolutions, aligning all three branches with lightweight structures. The change adds only a small parameter overhead but measurably improves classification of ripeness, a task that competes directly with localization for features in the original design.

The second front was the loss function. The baseline CIoU loss applies uniform regression constraints regardless of target scale or aspect ratio, which is a poor fit for small, irregularly shaped pitayas half-hidden behind branches. The authors substituted Shape-IoU, a loss that computes width and height weights from the ground-truth box and assigns a larger penalty to the short side of the fruit. A shape-weighted center-point distance term preferentially corrects short-side offsets, speeding convergence for low-overlap occluded fruits, while a decoupled size constraint term optimizes width and height errors independently, avoiding the mutual interference that plagues irregular targets. Crucially, Shape-IoU adds no network computation, and its scale adaptation factor handles mixed large and small fruits without retuning hyperparameters, an important convenience for agricultural deployment.

The third and fourth fronts targeted size. In the neck, the standard Bottleneck inside the C3k2 module was replaced with a FasterNet Block built on partial convolution, which convolves only one quarter of the input channels while passing the remaining three quarters through unchanged identity mapping, cutting floating-point operations by roughly 75 percent in that component. Then came compression: the LAMP layer-adaptive magnitude-based pruning algorithm scores each channel by within-layer normalized squared weight magnitude, allowing fair cross-layer comparison and globally coordinated removal of redundant channels. Pruning inevitably discards some useful features, so the team applied Masked Generative Distillation, in which a larger teacher model’s feature maps supervise a student whose features are randomly masked and then reconstructed through a small generation module, forcing the compact network to learn the intrinsic distribution of the teacher’s representations rather than pixel-level copies.

The ablation experiments trace each module’s contribution. The baseline YOLO11s achieved an mAP50 of 0.978 with 9.41 million parameters, 21.3 GFLOPs, and an 18.3 MB footprint. Adding TripleDetect lifted mAP50 to 0.981; Shape-IoU pushed it to 0.982 and raised the F1-score to 0.965 at no extra cost; C3_FasterBlock trimmed parameters to 8.76 million with negligible accuracy loss. Aggressive LAMP pruning at a rate of 0.9 then slashed the model to 3.72 million parameters, 9.5 GFLOPs, and 7.31 MB, but dropped mAP50-95 from 0.779 to 0.750. MGD distillation recovered much of that loss, restoring mAP50 to 0.981 and mAP50-95 to 0.758 without changing the architecture. The final YOLO11s-TSFL model improves mAP50 by 0.3 percentage points over the baseline while reducing parameters by 60.5 percent, computation by 55.4 percent, and model size by 60.1 percent.

Comparisons against mainstream lightweight detectors underscore the achievement. YOLO11s-TSFL posts an mAP50 of 0.981, ahead of YOLOv5s, YOLO12s, YOLO26s, and the original YOLO11s, and essentially on par with YOLOv8s, while using roughly one third of the parameters and computation of YOLOv8s and only 37.6 percent of the storage of YOLO26s. Its inference time of 30.6 milliseconds was the fastest of all models tested. On the untouched test set, overall precision reached 0.967 and recall 0.965, with ripe fruit detection especially strong at 99.2 percent mAP50. Raw fruit proved slightly harder, with precision of 0.948, largely because the green peel of unripe pitaya resembles the surrounding foliage. Confusion matrix analysis showed 97 percent classification accuracy for raw and 99 percent for ripe fruits, with residual misses concentrated in severely occluded or overexposed scenes. Grad-CAM heatmaps confirmed that the improved model concentrates its attention on the fruit peel and bracts across shallow, middle, and deep layers, suppressing the scattered background responses that distract the baseline network.

To demonstrate practical readiness, the team packaged the trained weights into a Windows 11 application that accepts local images, local video, or live camera input and outputs visual grading results with one-click archiving. The authors caution that the attention visualizations remain a technical inference, and that the link between peel-focused activation and agronomic ripeness indicators needs confirmation in field trials. They also note that validation across multiple orchards and growing seasons is still needed. Even so, the study makes a compelling case that carefully targeted architectural surgery, smart loss design, and a pruning-plus-distillation pipeline can compress a state-of-the-art detector to the point where it runs comfortably on the low-power computers that harvesting robots actually carry, bringing fully automated pitaya grading a decisive step closer to the field.

Subject of Research: A lightweight deep learning model for automated pitaya ripeness grading in orchard environments

Article Title: YOLO11s-TSFL: a lightweight deep learning model for pitaya ripeness grading in orchard environments

Article References: Qiu, Z., Liu, N., Mo, D., Li, J., Ma, X., & Tian, X. (2026). YOLO11s-TSFL: a lightweight deep learning model for pitaya ripeness grading in orchard environments. Smart Agricultural Technology, 15, Article 102627. https://doi.org/10.1016/j.atech.2026.102627

Image Credits: AI Generated

DOI: 10.1016/j.atech.2026.102627

Keywords: pitaya, dragon fruit, deep learning, YOLO11, object detection, ripeness grading, machine vision, model pruning, knowledge distillation, precision agriculture, harvesting robots, edge deployment

Machine vision systems combine image acquisition hardware, such as RGB cameras, multispectral and hyperspectral sensors, infrared thermography and even X-ray imaging, with software pipelines that clean, enhance and analyze the resulting images. The survey traces the classical workflow in detail. Raw images are first converted between color spaces or reduced to grayscale, then enhanced through techniques such as histogram equalization and its many adaptive variants, which stretch contrast while preserving brightness and structural detail. Noise introduced by dust, vibration and inconsistent field lighting is suppressed with Gaussian, median and Wiener-style filters, some of them optimized for real-time performance on embedded processors. Only after this preprocessing can the harder tasks begin: segmenting plants from soil, extracting features such as color, texture and shape, and classifying what the camera has actually seen.

Those downstream tasks have been transformed by the deep learning revolution. The survey documents the field’s migration from hand-engineered classifiers such as k-nearest neighbors, support vector machines, logistic regression and random forests toward convolutional neural networks, including landmark architectures such as AlexNet and the YOLO family of real-time object detectors, and more recently toward transformer-based and hybrid convolutional-transformer models. In plant disease detection alone, the authors cite systematic reviews showing that deep learning approaches now dominate the literature, with models trained on leaf imagery achieving rapid, automated diagnosis across crops as varied as tomato, grape, citrus, papaya and blueberry. Explainable deep vision frameworks have even been applied to plant stress phenotyping, giving breeders not just a prediction but a spatial map of where stress manifests on the plant.

Pest identification and monitoring emerges as one of the most mature application areas. Early systems relied on color cues to distinguish weeds from crops, while large-scale investigations demonstrated that machine vision could identify weed seeds with high accuracy. More recent work combines k-means clustering with convolutional neural networks for weed identification, enabling precision sprayers that apply herbicide only where weeds are detected rather than across entire fields. Smartphone-based systems now allow aphid identification and counting in the field, and light-attracted pest traps fitted with vision modules can automatically recognize and tally insect catches at high altitude in orchards. The practical payoff is a reduction in chemical inputs, lower costs and less environmental burden, all of which align with the sustainability goals that motivate precision agriculture in the first place.

The survey also charts how vision systems track crop growth and estimate yield, a problem with direct economic consequences. Researchers have measured seedling growth rates from images as early as the 1990s, and subsequent systems have monitored greenhouse vegetables, mushrooms and chrysanthemums non-destructively over time. Yield mapping began with citrus, where cameras counted fruit on the tree, and has since expanded to tomato yield estimation and fruit maturity detection using machine vision pipelines. Crop-load estimation with YOLOv8 illustrates the current state of the art: a single neural network counts fruit in real time from imagery captured on the move, giving growers a data-driven forecast of harvest volume before a single crate is filled. Systematic reviews of machine learning for crop yield prediction confirm that such vision-derived features are increasingly central to these forecasting models.

Perhaps the most visually dramatic applications involve harvesting robots, which must find fruit, localize it in three dimensions and guide a manipulator to pick it without damaging the crop. The review covers recognition and localization methods for fruit-picking robots across cucumber, apple, cotton, strawberry and citrus systems, including approaches that distinguish fruit from branch in cluttered natural scenes using support vector machines, and methods that reconstruct 3D models of fruit for precise grasping. Hyperspectral imaging paired with deep learning can even spot early bruises on apples that are invisible to the human eye, while X-ray and machine vision combinations probe internal fruit quality non-destructively. These capabilities matter because a robot that cannot reliably see ripe, undamaged fruit in variable lighting is a robot that cannot harvest at all.

Beyond the field, machine vision governs the quality grading and sorting lines that decide which products reach consumers. The survey documents multispectral real-time inspection of citrus dating back to the early 2000s, defect segmentation on apples, quality evaluation of soybeans, maturity prediction for harvested mangoes, and automatic grading of eggs, hairy crabs, walnuts, dragon fruit and litchi. Classical statistical tools such as principal component analysis and Gabor features once powered these systems; today, weighted k-means clustering, AlexNet-derived networks and automated machine learning pipelines sort produce by size, color, shape and surface defects at production-line speeds. Seed quality inspection has followed the same arc, with spectral detection of maize seed vigor and machine vision classification of seed defects enabling pre-planting screening that was previously impossible at scale.

Visual navigation for agricultural robots rounds out the survey’s application landscape. By extracting crop rows, navigation baselines and linear targets from camera imagery, machines can drive themselves through fields, orchards and paddy fields, often fusing vision with GPS for robustness. Stereo vision provides obstacle detection for off-road vehicles, and autonomous robotic mowers have demonstrated navigation and obstacle avoidance in orchards using purely visual cues. The authors note that this capability is converging with broader cyber-physical and Internet of Things architectures, in which vision-equipped machines, cloud analytics and renewable-energy-powered sensor networks form integrated cyber-agricultural systems capable of closing the loop from perception to action across entire farms.

The survey is candid about the obstacles that remain. Field lighting is notoriously inconsistent, motivating engineering fixes such as overcurrent-driven LEDs that guarantee stable image color and brightness. Datasets are often imbalanced or too small for the deep models being applied, and occlusion, clutter and the sheer biological variability of living crops continue to challenge even state-of-the-art detectors. The authors also flag the computational cost of running heavy neural networks on the embedded hardware that agricultural machinery can realistically carry, and the need for interpretable models that farmers can trust. Their forward-looking section points toward transformer architectures, multimodal sensor fusion combining hyperspectral and multispectral imagery, and tighter integration of vision with the cyber-physical systems that will define the next generation of autonomous agriculture.

What emerges from the full sweep of the review is a discipline in transition. The foundational image processing techniques of the 1990s and 2000s, from thresholding and edge detection to early neural classifiers, laid the groundwork; the deep learning era supplied the accuracy and generality that made commercial deployment plausible; and the current wave of transformers, explainable AI and cyber-physical integration is pushing machine vision toward farms that monitor, decide and act with minimal human intervention. For a world that must produce more food with fewer inputs on less land under a changing climate, the authors argue, teaching machines to see may prove one of the most consequential technologies agriculture has ever adopted.

Subject of Research: Machine vision applications in precision agriculture, including crop disease detection, yield estimation, robotic harvesting, quality grading and visual navigation

Article Title: A comprehensive survey on machine vision applications in precision agriculture: current trends and future perspectives

Article References: A comprehensive survey on machine vision applications in precision agriculture: current trends and future perspectives. (n.d.). https://doi.org/10.1007/s41060-026-01278-4

Image Credits: AI Generated

DOI: 10.1007/s41060-026-01278-4

Keywords: machine vision, precision agriculture, deep learning, computer vision, crop disease detection, yield estimation, harvesting robots, agricultural robotics, image processing, hyperspectral imaging, smart farming, artificial intelligence

The case for agricultural robotics rests on an uncomfortable arithmetic. Global population continues to climb while arable land per capita shrinks, and the research literature the authors draw upon cites stark figures on the interaction between food production, biodiversity protection, and demographic pressure. At the same time, crop losses to pests remain enormous, with published estimates in the review’s underlying literature suggesting that weeds, pathogens, and insects claim a substantial share of potential harvests worldwide. Machines that can patrol a field around the clock, distinguish a weed seedling from a crop plant with millimetre precision, and apply inputs only where needed promise a way to close that gap while reducing chemical use and soil compaction. It is this convergence of necessity and capability, the authors argue, that has moved agricultural robotics from an academic curiosity to a strategic imperative.

Harvesting remains the most visible and most demanding application. The review traces a lineage of fruit-picking machines stretching back more than two decades, including early autonomous cucumber harvesters developed in the Netherlands, robotic apple pickers demonstrated in Europe and Washington State, and strawberry-harvesting robots field-tested in Japan, where elevated-trough growing systems were specifically engineered to make fruit accessible to manipulators. The technical hurdles are formidable: fruit detection under variable lighting, occlusion by leaves and branches, collision-free motion planning for redundant seven-link manipulators, and end-effectors gentle enough not to bruise delicate produce. Modern systems increasingly fuse RGB-D cameras, structured-light vision, and LiDAR to localize fruit in three dimensions, while deep learning approaches trained on orchard imagery have dramatically improved detection rates for apples, mangoes, and sweet peppers. Yet the review notes that even the best prototypes still lag human pickers in speed and reliability, which is why commercial deployment has concentrated on high-value crops where labor scarcity is most acute.

Weeding, by contrast, has emerged as one of the closer-to-market successes. Because mechanical weed control replaces herbicides rather than replicating human dexterity, the tolerances are more forgiving. The review catalogs a rich history of vision-guided weeders, from early mobile robots with camera-based perception for mechanical weed control to four-wheel-steered platforms that detected weeds among sugar beet, and micro-robots designed for paddy fields in Asia. Recent systems use plant classification algorithms to identify crop rows and intra-row weeds, then actuate targeted hoes, tines, or micro-sprays. Improved convolutional neural networks have pushed maize seedling detection to new levels of accuracy under complex field conditions, and researchers have demonstrated robotic in-row weed control in commercial vegetable production. For organic farmers in particular, who cannot rely on selective herbicides, these machines represent a genuine transformation in weed management economics.

Precision seeding, transplanting, and field scouting round out the ground-robot portfolio documented in the review. Wheat precision-seeding robots have been tested at scale in China, autonomous rice seeders have operated in dry paddy fields in Thailand, and high-speed plug seedling transplanting robots have been designed and simulated for greenhouse nurseries. Phenotyping platforms such as the BoniRob field robot can measure individual plants repeatedly across a season, feeding plant breeders with data impossible to collect by hand. Coverage path planning has matured into a discipline of its own, with genetic algorithms optimizing driving angles and track sequences, and three-dimensional planning methods minimizing skipped or overlapped swaths on undulating terrain. Navigation, once dependent on buried cables or manual guidance, now relies on satellite positioning fused with machine vision and LiDAR-based tree recognition, allowing platforms to localize themselves inside orchards where sky visibility is compromised.

Above the crops, a parallel fleet has taken to the air. The review surveys the role of unmanned aerial vehicles in remote sensing and precision agriculture, including autonomous UAVs with onboard vision-based decision making and fleets of mini aerial robots coordinated for efficient area coverage. Drone-acquired imagery, analyzed with spectral-spatial methods, has been used to detect and count tomatoes from the sky, while LiDAR and vision sensors mounted on aircraft and ground vehicles have mapped almond orchard canopy volume, flower density, and yield. Vineyard yield estimation by dedicated scouting robots has moved into preliminary commercial trials in Europe. Together, these aerial systems give growers a synoptic view of field variability that ground robots complement with close-range, high-resolution measurements, forming what the authors describe as an increasingly integrated sensing and actuation architecture.

Livestock management, though less glamorous, is identified as a growing frontier. Autonomous robots have been tested for measuring air quality inside livestock buildings, navigating the cluttered, dusty, and corrosive environments of animal housing with surprising accuracy. The review notes that such applications demand robustness traits quite different from field machinery, including resistance to ammonia, washdown sanitation, and safe operation around unpredictable animals. Meanwhile, cooperative robotics, in which multiple machines share tasks and information, is flagged as an emerging paradigm that could let small, cheap robots collectively accomplish what would otherwise require an expensive, heavy single platform, thereby reducing soil compaction and spreading risk across redundant units.

The heart of the review lies in its unsparing analysis of what still blocks adoption. Technically, agricultural environments are adversarial: mud, dust, rain, and unstructured vegetation confound sensors designed for factory floors; energy density limits endurance; and perception systems must generalize across cultivars, seasons, and lighting regimes. Economically, the authors point to long-standing feasibility studies showing that agricultural robots must compete with machinery whose costs are amortized over enormous acreage, and that adoption depends on farm size, labor markets, and payback periods that vary wildly between regions. Regulatory considerations, from safety certification of machines operating near humans to liability for autonomous decisions, remain fragmented and largely undeveloped. The review also highlights data ownership and interoperability questions as machines from different manufacturers must eventually share fields, infrastructure, and information.

The path forward, the authors conclude, runs through artificial intelligence, machine learning, and their fusion with the Internet of Things and big data analytics. Recent literature they cite documents AI-driven autonomous robots for precision agriculture, machine learning methods for crop disease detection, and IoT-enabled smart irrigation systems that couple sensor networks with robotic actuation. But the review’s most emphatic recommendation is interdisciplinary: robust algorithms, standardized protocols, and cost-effective designs will emerge only when roboticists work alongside agronomists, economists, and policymakers rather than in parallel silos. If that collaboration materializes, the authors argue, agricultural robotics can underpin farming systems that are simultaneously more productive, more sustainable, and more resilient to labor shortages and climate stress, turning a generation of promising prototypes into the quiet workhorses of the world’s farms.

Subject of Research: Application of robotics, artificial intelligence, and automation technologies to agriculture, including crop monitoring, precision farming, harvesting, and livestock management

Article Title: A state-of-the-art review on robotics in agriculture: research challenges and future directions

Article References: Kamaruzzaman, M., Pandey, S., & Azharuddin, M. (2026). A state-of-the-art review on robotics in agriculture: research challenges and future directions. International Journal of Intelligent Robotics and Applications. https://doi.org/10.1007/s41315-026-00584-1

Image Credits: AI Generated

DOI: 10.1007/s41315-026-00584-1

Keywords: agricultural robotics, precision agriculture, harvesting robots, weeding robots, crop monitoring, artificial intelligence, machine learning, Internet of Things, UAV drones, livestock management, field robotics, sustainable farming