The early and precise identification of the different phenological stages of the bean (Phaseolus vulgaris L.) allows for the determination of critical and timely moments for the implementation of certain agricultural activities that contribute in a significant manner to the output and quality of the harvest, as well as the necessary actions to prevent and control possible damage caused by plagues and diseases. Overall, the standard procedure for phenological identification is conducted by the farmer. This can lead to the possibility of overlooking important findings during the phenological development of the plant, which could result in the appearance of plagues and diseases. In recent years, deep learning (DL) methods have been used to analyze crop behavior and minimize risk in agricultural decision making. One of the most used DL methods in image processing is the convolutional neural network (CNN) due to its high capacity for learning relevant features and recognizing objects in images. In this article, a transfer learning approach and a data augmentation method were applied. A station equipped with RGB cameras was used to gather data from images during the complete phenological cycle of the bean. The information gathered was used to create a set of data to evaluate the performance of each of the four proposed network models: AlexNet, VGG19, SqueezeNet, and GoogleNet. The metrics used were accuracy, precision, sensitivity, specificity, and F1-Score. The results of the best architecture obtained in the validation were those of GoogleNet, which obtained 96.71% accuracy, 96.81% precision, 95.77% sensitivity, 98.73% specificity, and 96.25% F1-Score.

Lane keeping under degraded visual confidence remains challenging because most existing approaches focus either on improving lane-feature extraction or on estimating vehicle motion, while giving less attention to how unreliable visual measurements should modify the estimator–controller interaction in a physical closed-loop system. This paper presents a confidence-gated Kalman lane-keeping architecture for a 1:10-scale autonomous vehicle. The methodological contribution lies in the direct coupling of visual confidence, state estimation, and steering control: unreliable lane measurements are down-weighted through confidence-dependent measurement noise, while the propagated lane-relative state remains available to the controller. The primary experimental unit is the run, defined as one logged lap under one control configuration; frame-level summaries are retained only as historical reproducibility material. In the run-level comparison, the autonomous vision, inertial measurement unit (IMU)-feedforward, and Kalman filter (KF) group KF_G1—the first inferential KF generation—had lower mean absolute error than the human baseline, while vision and KF_G1 had overlapping run-level confidence intervals for absolute error. KF_G1 shifted the mean signed bias closer to the lane reference than the vision and IMU groups, but with higher run-level spread than vision. KF_G2, the second observational KF generation, is reported only as an observational generation comparison, so no causal claim is made for its estimator–controller correction weight $K_s=0.15$ setting. KF_G3, the single descriptive adverse-condition KF run, is reported without an estimable confidence interval or population-level adverse-illumination inference. A further limitation is that the inertial prediction pathway was inactive in the logged Kalman-filter runs because the inertial coupling coefficient $\alpha =0$. The main contribution is a reproducible run-level evaluation of confidence-gated estimator–controller coupling that distinguishes supported evidence from observational and descriptive cases.

This work presents a reproducible YOLO-based pipeline for bottle detection in sandy environments, emphasizing dataset integrity, leakage-free evaluation, and deployment-oriented model selection. A one-class dataset of 1585 images and 3167 annotated bottles was audited to identify annotation-format defects and near-duplicate contamination between training and validation partitions. Sequence membership was reconstructed through perceptual-image similarity and used to assign complete image components to a sequence-aware train/validation split, eliminating the near-duplicate pairs found in the initial random partition. A controlled ablation holding model, seed, and corrected labels fixed showed that the random split reports 0.040 higher mAP@0.5:0.95 than the sequence-aware split (0.787 vs. 0.747), quantifying the leakage risk directly rather than only asserting it. Five YOLO configurations were then benchmarked under three independent seeds each; the observed mAP@0.5:0.95 differences among models (0.004–0.008) were small in absolute magnitude and, given only three seeds per model, are interpreted descriptively rather than as evidence of statistical equivalence or significance, so yolo11n_bottle was selected through a joint accuracy-parity, compactness, and exportability criterion (precision 0.982, recall 0.985, mAP@0.5 0.992, mAP@0.5:0.95 0.748), using approximately ten times fewer parameters than the largest configuration and producing a 5.2 MB checkpoint. ONNX export preserved detection geometry closely (100% count agreement, mean matched IoU $\ge 0.9998$), without meeting strict metric-parity tolerances. A stratified sample of 108 frames from operational RealSense BAG footage was manually annotated by an independent reviewer and evaluated quantitatively: mAP@0.5 remained close to the internal validation figure (0.927 vs. 0.992), while mAP@0.5:0.95 fell substantially (0.483 vs. 0.747), revealing a localization gap between the curated benchmark and operational conditions that this manuscript reports transparently. Together, these results show that dataset auditing, sequence-aware partitioning, multiseed benchmarking, and manually annotated operational evidence are each necessary to interpret a detection benchmark built from continuous video acquisition, providing a traceable, reproducible workflow for selecting and evaluating compact visual-perception models for resource-constrained environmental applications.