Search Results (640)

Pedestrian detection is a fundamental component of Advanced Driver Assistance Systems (ADAS) and plays a key role in collision avoidance and the safety of vulnerable road users. This paper presents a structured review of pedestrian detection methodologies developed between 2000 and 2025, spanning classical vision techniques and modern deep learning architectures. We organize the review into two phases. First, we examine classical methods, including Histogram of Oriented Gradients (HOG)+Support Vector Machine (SVM), Viola–Jones, Deformable Part Models, and Integral Channel Features, which established the conceptual foundations of the field. Then, we analyze state-of-the-art deep learning architectures, categorized by detector stage (one-stage vs. two-stage), localization strategy (anchor-based vs. anchor-free), feature extraction paradigm (Convolutional Neural Network (CNN)-based vs. transformer-based), output representation (bounding box vs. instance segmentation), and computational profile (lightweight vs. heavyweight). Several design principles introduced by classical methods remain visible in modern architectures, indicating that they were not fully superseded. The review also examines publicly available benchmark datasets and compares the strengths and limitations of camera-, Light Detection And Ranging (LiDAR)-, radar-, and multi-sensor-fusion-based systems for ADAS deployment. We close by identifying six open problems for the field: adversarial robustness, real-time inference under embedded constraints, detection under adverse weather, dataset bias and demographic fairness, the deployment of Bird’s-Eye View (BEV) and unified perception on automotive hardware, and explainability for safety-critical use. Full article

Accurate junction temperature ($T_j$) sensing is essential for the reliability of silicon carbide (SiC) power modules in electric vehicles. Nonetheless, the physical separation and consequent thermal signal delay between sensing elements and chips pose significant challenges to precise junction temperature monitoring. To solve this issue, an embedded temperature sensing structure integrated into the designed double-sided cooling (DSC) SiC power module is proposed, which leverages 3D vertical interconnects to enhance temperature observability. The customized design of a copper spacer serves as the primary heat dissipation path and electrical connection between the upper and lower chips in the same location. A compact thermal resistance network and 3D finite-element simulations are developed to reveal the vertical thermal coupling between the spacers and the chips, enabling accurate junction temperature estimation from spacer temperature. The proposed concept is experimentally validated on a fabricated prototype using embedded K-type thermocouples and an IR camera under power cycling conditions. The measured temperature differences between the copper spacers and the junction temperature are maintained within approximately 0.5–2 °C under the tested operating range. This approach provides a potential application in real-time condition monitoring and thermal management in high-power-density electric drives. Full article

Recently, deep learning has enabled unmanned aerial vehicles (UAVs) to detect human bodies in aerial imagery, which is of particular importance in post-disaster situations such as floods and storms. Yet progress in this domain remains constrained by a familiar obstacle: the shortage of annotated training data. Neural networks, while powerful, are highly sensitive to data volume and diversity. Existing augmentation strategies help reduce this gap but typically introduce only incremental novelty, especially with respect to viewpoint variation, thereby limiting dataset richness. In this work, we propose a complementary strategy that leverages three-dimensional human models reconstructed via photogrammetric techniques. By situating these models within a controlled rendering environment, we generate synthetic imagery across a broad range of elevations and camera angles—perspectives that are rarely captured in conventional UAV datasets. These additions are designed to increase both the variability and the resilience of the training corpus. To evaluate the contribution of this approach, a custom CNN deep convolutional neural classifier was trained and benchmarked on a UAV human vs. non-human patch dataset of 4000 baseline images (128 × 128 px; 2800 train, 600 validation, 600 test), expanded with 3000 photogrammetry-derived synthetic patches (balanced by class) to 7000 total images for the 3DG setting. The primary metric was classification accuracy on the held-out test set, consistent with patch-level evaluation practice; detection-style metrics such as AP/IoU were not applicable to this binary classification protocol. Averaged over five independent training runs, the proposed augmentation improved classification accuracy by 3.02 percentage points over the baseline (88.06 ± 0.97% → 91.08 ± 1.03%), with consistent gains in precision, recall, and F1-score. When combined with standard augmentations (rotation, translation, scaling, flipping), accuracy reached 95.21 ± 0.61%, a gain of 7.15 percentage points over the baseline. These results suggest that photogrammetry-based augmentation offers a practical and effective enhancement for UAV-based human detection pipelines where timely, reliable identification is critical. Full article

Autonomous driving systems rely on a sophisticated pipeline of artificial intelligence models to perceive, predict, and plan in dynamic environments. This review presents a systematic analysis of the machine learning and deep learning models underpinning vehicle autonomy, spanning classical convolutional neural networks (CNNs) for object detection and semantic segmentation to recurrent and Transformer-based architectures for trajectory prediction and motion planning. It also provides a critical examination of the autonomous vehicle sensor stack, including cameras, LiDAR, radar, ultrasonics, and GNSS/IMU as data acquisition systems, highlighting modality-specific AI challenges such as monocular depth estimation, 3D point cloud processing, and radar Doppler interpretation. The evolution of perception and decision-making pipelines is reviewed, contrasting modular architectures with end-to-end learning paradigms that directly map raw sensor data to control commands, and discussing their trade-offs in interpretability, safety assurance, and robustness to rare edge cases. We further survey specialized hardware accelerators and heterogeneous automotive SoCs designed to meet stringent real-time and power constraints. Industrial strategies are compared, including multi-modal sensor fusion and vision-centric approaches based on large-scale imitation learning. Finally, we identify open challenges related to robustness under adverse conditions, domain shift, causal ambiguity, and the need for interpretable and certifiable AI in safety-critical autonomous driving systems. Full article

Marine pollution monitoring increasingly relies on Biological Early Warning Systems (BEWSs), which use living organisms as continuous, integrative sentinels of water quality. The moon jellyfish Aurelia aurita is a sensitive but under-exploited candidate for this role. We present a computer-vision BEWS pipeline that is unsupervised at inference time and operates without labelled pollution-response data, converting side-view aquarium video of single A. aurita medusae into a binary pollution alarm. Per-frame YOLO bounding-box detections are reduced to a continuous bell-area signal and a centroid trajectory, from which eleven pulsation, kinematic, and detection-quality features are extracted on 60 s sliding windows. A per-animal baseline is fitted on a clean-water baseline (recommended ≥15 min), and a two-layer detector—fast outlier detection on the mean absolute z-score with a k-of-N rule, plus one-sided CUSUM (cumulative sum) accumulation—flags any sustained deviation. Validation on six adult medusae exposed to diesel-WAF detected all six animals (95% CI 54–100%) and produced no false alarms in 203 clean-window opportunities (exact 95% upper bound 1.8%; rule-of-three estimate ≈1.5%). First-alarm latencies ranged from 1.0 to 23.7 min, and the observed responses were described as three descriptive patterns in this pilot dataset: sharp step-change, slow drift, and mixed. The deployed anomaly scoring step contains no neural-network weights, runs in under 300 lines of Python, and is designed for field-portable use in settings where a stationary side-view camera can be positioned alongside an aquarium, although field validation remains required. Per-animal anomaly detection accommodates the strong inter-individual variability of the diesel-WAF response that limits supervised clean-versus-polluted classification at this sample size. Full article

The objective of white balance is to accurately estimate and subsequently eliminate the color of global illumination present in an image. Learning-based methods have gained prominence over statistical approaches due to their typically superior accuracy. However, these methods rely on high-quality, large datasets. The quality of a dataset is intrinsically tied to the volume of knowledge it encapsulates, specifically the uniformity in the distribution of labels. In this study, we expand the dataset by leveraging the camera imaging pipeline. Subsequently, we segment the image into 16 partially overlapping blocks that collectively encompass the entire image. We then propose a rudimentary neural network designed to train these blocks with consistent labels, yielding 16 predictive outcomes that serve as image features. These features are used to capture complex illumination and reflection data within the image. Utilizing these features, we employ a straightforward, fully connected neural network to calculate the color mapping function, thereby correcting the image colors. Experimental results show that the methodology proposed in this paper significantly surpasses existing state-of-the-art color constancy methods. Full article

Laser powder bed fusion (L-PBF) has emerged as a core metal additive manufacturing technology for high-end sectors, including aerospace and medical device manufacturing. However, melting anomalies that occur during fabrication accumulate layer by layer, leading to degraded surface quality and impaired mechanical performance of as-built components—a critical bottleneck limiting their large-scale industrial adoption. Accurate and robust layer-wise melting quality recognition remains a challenge due to the complex surface morphologies induced by such melting anomalies. This study presents a machine learning-enabled in situ monitoring approach for layer-wise melting quality identification in L-PBF. By systematically varying laser power and scanning speed, 24 parameter combinations were designed to fabricate specimens with three distinct melting states: over-melting (OM), lack of fusion (LOF), and normal melting. A high-resolution complementary meta–oxide–semiconductor (CMOS) camera was used to capture layer-wise surface images of the specimens, and following abnormal layer filtering and manual validation, a high-quality dataset comprising 5110 layer-wise images was constructed. Two mainstream machine learning approaches were systematically evaluated and optimized for melting quality classification: a support vector machine (SVM) model leveraging handcrafted gray-level co-occurrence matrix (GLCM) texture features achieved a classification accuracy of 96.77%, while a convolutional neural network (CNN) model with end-to-end feature learning directly from raw images attained a superior accuracy of 98.14%. In terms of computational efficiency, the CNN model exhibited a faster inference speed with a per-layer inference time of just 0.036 s, nearly half that of the SVM model (0.068 s per layer). Most critically, the CNN model completely eliminated fatal cross-class misclassification between OM and LOF—an error mode common in the SVM model that would trigger erroneous process corrective actions in practical industrial applications. The findings demonstrate that image-based machine learning provides a reliable technical foundation for intelligent in situ monitoring of the L-PBF process. With its high accuracy, strong robustness, and superior computational efficiency, the CNN model can effectively support on-site operational decision-making, reduce material and time losses, and enhance process stability in industrial settings, thus exhibiting significant potential for practical engineering deployment. Full article

To address the issues of traditional high-resolution spatial remote sensing cameras—complex optical systems, heavy weight, long development cycles, and high costs—this study combines the optical design parameters and product characteristics of lightweight remote sensing payloads. Based on the “physical simplification–algorithm enhancement” computational imaging paradigm, an algorithm-side enhancement technical system tailored to these lightweight payloads is constructed. This paper establishes a point-spread function (PSF) model for simplified optical systems and a dedicated imaging degradation model, verifying the compensation mechanism of computational methods against optical degradation effects. It achieves high-performance imaging through “low-precision simplified optics + high-precision algorithms,” providing theoretical support and practical implementation pathways for lightweight, low-cost, and rapid-response spaceborne remote sensing payloads. Experimental results confirm the excellent imaging performance of the camera, validating the effectiveness of the proposed optical design. Compared with the baseline Mask R-CNN (region-convolution neural networks), the AP50 and overall AP (average precision) of the AS Mask R-CNN are improved by 4.0% and 1.0%, respectively. This research offers a robust technical solution for intelligent remote sensing camera modes and serves as valuable reference and technical support for the opto-mechanical co-design of high-resolution remote sensing payloads. Full article

This article presents the design, implementation, and experimental validation of an autonomous drone system for search and rescue operations in cluttered GNSS-denied environments. The proposed platform integrates advanced navigation, mapping, and victim-detection capabilities, leveraging a suite of RGB-D cameras and edge-AI computation for real-time perception and decision-making. A key contribution is the integration of an eye-blink-detection pipeline for onboard assessment of the consciousness states of detected victims, enabling the drone to prioritize rescue efforts based on victim alertness. The system employs a modular software architecture with a pipeline that combines a U-Net segmentation network with a MultiScaleLSTM classifier, achieving approximately 97.73% accuracy and a combined inference latency of 6.35 ms on the NVIDIA Jetson Xavier-NX. Experimental results demonstrate the drone’s ability to autonomously explore unknown environments, accurately detect and classify victims, and operate effectively in real-world scenarios. The article also discusses observed challenges, such as computational bottlenecks and false positive detections, and outlines future directions for improving system robustness and autonomy. Full article

Maritime aerial imaging is strongly affected by rapid illumination variations induced by dynamic sea conditions, which often cause conventional exposure control approaches to misinterpret intrinsic scene brightness as overexposure resulting from elevated camera settings. To overcome this issue, an adaptive exposure control framework based on a Glare-Aware Attention Network is proposed, implemented within an end-to-end dual-branch architecture. The framework utilizes an Exposure State Encoding (ESE) module to encode the current frame’s exposure parameters as conditional vectors, thereby resolving physical ambiguities in scene understanding. A Glare-Aware Spatial Attention (GASA) mechanism is further introduced, incorporating a glare prior map (GPM) generated using a “high-luminance, low-texture” heuristic to explicitly suppress sun glint effects. A Scene Difficulty-Adaptive Loss Weighting (SDAW) scheme is designed to adaptively regulate loss weights, and region-aware evaluation metrics, KREA and ISR, are defined. On a self-collected maritime aerial imaging dataset, the proposed approach significantly outperforms both traditional and deep learning-based methods in terms of full-frame and region-level performance metrics. Compared with the multi-task CNN baseline that has the closest parameter count, it achieves a 1.7 dB gain in PSNR. Cross-dataset validation on SeaDronesSee, temporal consistency analysis, and embedded platform testing further support the generalization and real-time feasibility of the proposed solution. Offering a high-accuracy, region-aware exposure control solution for aerial cameras in complex sea surface scenarios. Full article

Digital camera sensors are designed to capture a wide range of incident illuminants, enabling the creation of high-quality images. However, these sensors lack the capability to differentiate between the color of the source illuminant and the actual color (or original color) of the object being captured. For this reason, the computational color constancy (CCC) was introduced and has been developed over decades. The CCC is an approach to modeling the color perception of the human visual system (HVS) by ensuring accurate object color determination under varying source illuminant conditions. At the core of human visual perception (HVP)-based CCC is attaining higher accuracy in scene illuminant estimation. The emergence of deep convolutional neural networks (DCNNs) was a recent innovation in accurate illuminant estimation, fundamentally transforming the CCC research landscape. Nevertheless, accurate illuminant estimation still remains a huge challenge for both traditional and state-of-the-art (SOTA) approaches. To further advance precision in illuminant estimation, this article presents a novel learning-based illumination color cast estimation approach to HVP-based CCC. Most importantly, the proposed approach is intended to integrate informative features into both channel and spatial regions while preserving long-term dependency feature information with the use of dense skip connections. To achieve these objectives, the proposed Dense Dual Connection Aggregated Transform Network (DDCATNet) architecture is designed to comprise several modules: shallow feature extraction, channel-wise and spatial feature-based Dense Dual Connection (DDC), fusion of the dense channel-wise attention (CA) and spatial attention (SA) branches through a gate mechanism (GM) unit, and aggregate transform. It is worth noting that both the CA blocks and the SA blocks in the DDC module are characterized by dense and cascading connections, meant to preserve long-term feature information and modulate different-level feature information at both global and local scales. The densely connected CA branch (DCA) and the densely connected SA branch (DSA) are also highly effective in securing high-contribution information while suppressing redundant data. The GM unit is integrated at the back of the DDC module, fusing the two DCA and DSA branches to ensure the adaptive merging of useful hierarchical feature information and the extraction of more valuable feature information. As a result, the proposed DDCATNet architecture significantly enhanced precision in illuminant estimation, thereby improving performance. In rigorous experiments on a wide range of datasets, the proposed DDCATNet approach outperformed its SOTA counterparts, validating the efficacy and generalization capabilities, as well as robust camera-invariance, across diverse, single- and multi-illuminant datasets and model architectures. Full article

Perception-oriented evaluation of automotive headlamps still relies mainly on human-vision photometric criteria, although forward-facing cameras are increasingly safety-critical sensing elements for night driving. This paper benchmarks 16 measured production headlamp light distributions with a simulation chain that combines headlamp spectra and beam patterns, diffuse scene reflection, an imaging-transfer model, and an EMVA-based camera model. The quantitative chain maps scene radiance to sensor-domain signal-to-noise ratio, derives task-specific required signal-to-noise curves from a six-network object-recognition ensemble, and aggregates local threshold satisfaction as region-of-interest coverage across three target reflectances and five driving speeds using WLTP moving-time weights. For the baseline RGB camera, WLTP-weighted coverage ranges from 18.95% to 53.48% across the evaluated light distributions, corresponding to a factor of 2.82 between the weakest and strongest distribution. The camera-parameter sweeps show that favorable beam placement can deliver comparable benchmark coverage with roughly 60% smaller pixel pitch than the weakest distribution, corresponding to an 84% reduction in pixel area, or at materially shorter exposure times. The WLTP-weighted coverage score correlates positively with the established Headlamp Safety Performance Rating, with Pearson $r=0.68$ for the RGB configuration, indicating partial alignment between human-centric and camera-centric illumination needs while confirming that the metrics are not interchangeable. The results identify headlamp light distribution as a primary design parameter for nighttime camera perception and provide a quantitative basis for co-design of automotive lighting and camera-based systems. Full article

Accurate road segmentation is a core perceptual technology for autonomous driving, but faces two challenges: (1) ambiguous road boundaries caused by insufficient modeling of contextual information relationships in CNN-based networks and (2) inadequate LiDAR-camera fusion due to modality gaps between heterogeneous sensors. To mitigate these limitations, this paper proposes a novel approach, named LiDAR-Camera High-Resolution Feature Fusion Network (LC-HR2FNet), a multi-cross-stage fusion model designed for road segmentation. Firstly, a new type of pseudo-LiDAR-Image representation is generated via an early-level fusion strategy and data complementation. Sparse point clouds are transformed into dense LiDAR-Image data and then concatenated with RGB channel maps to form complementary multi-modal data inputs. Subsequently, a modified HRNet backbone integrated with cross-stage feature fusion is constructed to strengthen information interaction across different branches and enhance the modeling of contextual relationships. Additionally, a dilated feature collection model is designed to collect multi-scale confidence scores for pixel-wise class determination. Experiments on the KITTI road benchmark demonstrate that the proposed method achieves a MaxF of 97.39% on UMM_ROAD and an average of 96.28% across all urban scenarios, demonstrating superior performance and robustness. Full article

Plant leaf starch content is a critical indicator of metabolic status, yet traditional enzymatic methods are destructive, labor-intensive, and costly. This study proposes a novel non-destructive detection method using watermelon–pumpkin grafted seedlings. To optimize hardware design, 12 characteristic wavelengths were identified via competitive adaptive reweighted sampling (CARS). A portable multispectral imaging system was developed, featuring narrowband LEDs and integrated human–computer interaction software for real-time visualization. We constructed a multimodal deep learning architecture that integrates a convolutional neural network (CNN) for spatial feature extraction from RGB images, a fully connected neural network (FCNN) for spectral data, and a Transformer network for high-level feature fusion. Experimental results showed that the ShuffleNet v2-Transformer model achieved an R² of 0.956 (RMSE = 0.036) for watermelon leaves, while the EfficientNet b1-Transformer model reached an R² of 0.967 (RMSE = 0.052) for pumpkin leaves. This multimodal approach significantly outperformed conventional PLSR and single-modal CNN models, demonstrating superior ability in processing long-range dependencies within spectral–spatial data. The system enables accurate detection with a throughput of 120 samples per hour at a hardware cost approximately 90% lower than commercial multispectral cameras. This provides an efficient, low-cost solution for large-scale monitoring of plant physiological indicators in precision breeding. Full article

This paper details the implementation of an integrated engineering framework for the real-time assessment of pose and size in fusiform fish, utilizing laser-camera technology. The design, comprising a camera and laser emitter, leverages laser triangulation for accurately measuring distances between key points, providing a reliable baseline for data comparison. Enhanced with the yolov7 model backbone, it includes detection and segmentation features, enabling precise image instance segmentation of fish and laser lines. The system’s dual-network structure, which combines fully connected regression and DSNT-MobileFaceNet networks, efficiently identifies six crucial landmarks on fish—an essential step for detailed pose analysis. This method facilitates the accurate determination of two-dimensional fish posture by analyzing the relative positions of these landmarks. A notable capability of this system is its ability to infer depth information from laser lines on the fish’s body, aiding in the accurate measurement of dimensions such as body length and depth. Empirical results demonstrate the system’s effectiveness, with high mean Average Precision (mAP) values for both object detection (0.9560 for fish, 0.8550 for laser lines) and segmentation (0.9740 for fish, 0.8420 for laser lines). The DSNT-MobileFaceNet network, in particular, shows excellent fitting accuracy with an $R^2$ value of 0.9170. The deep learning model achieves an average error rate of 7.75% in detecting fish data, markedly improving upon the baseline error rate of 14.70%. Overall, this study confirms the proposed system’s capability in accurately assessing fish pose and size. As a rigorous proof of concept validated in a controlled laboratory environment, this work establishes a foundational framework for non-invasive morphological monitoring, suggesting its future applicability in marine biology and aquaculture. Full article