In recent years, active research has been conducted on computer vision and artificial intelligence (AI) for autonomous driving to increase the understanding of the importance of object detection technology using a frontal-viewing camera. However, using an RGB camera as a frontal-viewing camera can generate lens flare artifacts due to strong light sources, components of the camera lens, and foreign substances, which damage the images, making the shape of objects in the images unrecognizable. Furthermore, the object detection performance is significantly reduced owing to a lens flare during semantic segmentation performed for autonomous driving. Flare artifacts pose challenges in their removal, as they are caused by various scattering and reflection effects. The state-of-the-art methods using general scene image retain artifactual noises and fail to eliminate flare entirely when there exist severe levels of flare in the input image. In addition, no study has been conducted to solve these problems in the field of semantic segmentation for autonomous driving. Therefore, this study proposed a novel lens flare removal technique based on a class attention map-based flare removal network (CAM-FRN) and a semantic segmentation method using the images in which the lens flare is removed. CAM-FRN is a generative-based flare removal network that estimates flare regions, generates highlighted images as input, and incorporates the estimated regions into the loss function for successful artifact reconstruction and comprehensive flare removal. We synthesized a lens flare using the Cambridge-driving Labeled Video Database (CamVid) and Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago (KITTI) datasets, which are road scene open datasets. The experimental results showed that semantic segmentation accuracy in images with lens flare was removed based on CAM-FRN, exhibiting 71.26% and 60.27% mean intersection over union (mIoU) in the CamVid and KITTI databases, respectively. This indicates that the proposed method is significantly better than state-of-the-art methods.

There are few studies utilizing only IR cameras for long-distance gender recognition, and they have shown low recognition performance due to their lack of color and texture information in IR images with a complex background. Therefore, a rough body segmentation-based gender recognition network (RBSG-Net) is proposed, with enhanced gender recognition performance achieved by emphasizing the silhouette of a person through a body segmentation network. Anthropometric loss for the segmentation network and an adaptive body attention module are also proposed, which effectively integrate the segmentation and classification networks. To enhance the analytic capabilities of the proposed framework, fractal dimension estimation was introduced into the system to gain insights into the complexity and irregularity of the body region, thereby predicting the accuracy of body segmentation. For experiments, near-infrared images from the Sun Yat-sen University multiple modality re-identification version 1 (SYSU-MM01) dataset and thermal images from the Dongguk body-based gender version 2 (DBGender-DB2) database were used. The equal error rates of gender recognition by the proposed model were 4.320% and 8.303% for these two databases, respectively, surpassing state-of-the-art methods.

In precision agriculture, semantic segmentation enhances the crop yield by enabling precise disease monitoring, targeted herbicide application, and accurate crop–weed differentiation. This enhances yield; reduces the overuse of herbicides, water, and fertilizers; lowers labor costs; and promotes sustainable farming. Deep-learning-based methods are particularly effective for crop and weed segmentation, and achieve potential results. Typically, segmentation is performed using homogeneous data (the same dataset is used for training and testing). However, previous studies, such as crop and weed segmentation in a heterogeneous data environment, using heterogeneous data (i.e., different datasets for training and testing) remain inaccurate. The proposed framework uses patch-based augmented limited training data within a heterogeneous environment to resolve the problems of degraded accuracy and the use of extensive data for training. We propose an attention-driven and hierarchical feature fusion network (AHFF-Net) comprising a flow-constrained convolutional block, hierarchical multi-stage fusion block, and attention-driven feature enhancement block. These blocks independently extract diverse fine-grained features and enhance the learning capabilities of the network. AHFF-Net is also combined with an open-source large language model (LLM)-based pesticide recommendation system made by large language model Meta AI (LLaMA). Additionally, a fractal dimension estimation method is incorporated into the system that provides valuable insights into the spatial distribution characteristics of crops and weeds. We conducted experiments using three publicly available datasets: BoniRob, Crop/Weed Field Image Dataset (CWFID), and Sunflower. For each experiment, we trained on one dataset and tested on another by reversing the process of the second experiment. The highest mean intersection of union (mIOU) of 65.3% and F1 score of 78.7% were achieved when training on the BoniRob dataset and testing on CWFID. This demonstrated that our method outperforms other state-of-the-art approaches.

Recently, research on the methods that use images captured during day and night times has been actively conducted in the field of person re-identification (ReID). In particular, ReID has been increasingly performed using infrared (IR) images captured at night and red-green-blue (RGB) images, in addition to ReID, which only uses RGB images captured during the daytime. However, insufficient research has been conducted on ReID that only uses IR images because their color and texture information cannot be identified easily. This study thus proposes an original and attention-guided DenseNet-based ensemble network (OADE-Net)—a ReID model that can recognize pedestrians using only IR images captured during the day and night times. The OADE-Net consists of the original and attention-guided DenseNets and a shallow convolutional neural network for the ensemble network (SCE-Net), which is a model used for combining the two models. Owing to the lack of existing open datasets that only consist of IR images, the experiments are conducted by creating a new dataset that only consists of IR images retrieved from two open databases (DBPerson-Recog-DB1 and SYSU-MM01). The experimental results of the OADE-Net showed that the achieved ReID accuracy of the DBPerson-Recog-DB1 is 79.71% in rank 1, while the mean average precision (mAP) is 78.17%. Furthermore, an accuracy of 57.30% is achieved in rank 1 in the SYSU-MM01 case, whereas the accuracy of the mAP was 41.50%. Furthermore, the accuracy of the OADE-Net in both datasets is higher than that of the existing score-level fusion and state-of-the-art methods.

Research on semantic segmentation for remote sensing road scenes advanced significantly, driven by autonomous driving technology. However, motion blur from camera or subject movements hampers segmentation performance. To address this issue, we propose a knowledge distillation-based semantic segmentation network (KDS-Net) that is robust to motion blur, eliminating the need for image restoration networks. KDS-Net leverages innovative knowledge distillation techniques and edge-enhanced segmentation loss to refine edge regions and improve segmentation precision across various receptive fields. To enhance the interpretability of segmentation quality under motion blur, we incorporate fractal dimension estimation to quantify the geometric complexity of class-specific regions, allowing for a structural assessment of predictions generated by the proposed knowledge distillation framework for autonomous driving. Experiments on well-known motion-blurred remote sensing road scene datasets (CamVid and KITTI) demonstrate mean IoU scores of 72.42% and 59.29%, respectively, surpassing state-of-the-art methods. Additionally, the lightweight KDS-Net (21.44 M parameters) enables real-time edge computing, mitigating data privacy concerns and communication overheads in internet of vehicles scenarios.

Improving the decoding accuracy of biological signals has been a research focus for decades to advance health, automation, and robotic industries. However, challenges like inter-subject variability, data scarcity, and multifunctional variability cause low decoding accuracy, thus hindering the practical deployment of biological signal paradigms. This paper proposes a multifunctional biological signals network (Multi-BioSig-Net) that addresses the aforementioned issues by devising a novel blind few-shot learning (FSL) technique to quickly adapt to multiple target domains without needing a pre-trained model. Specifically, our proposed multimodal similarity extractor (MMSE) and self-multiple domain adaptation (SMDA) modules address data scarcity and inter-subject variability issues by exploiting and enhancing the similarity between multimodal samples and quickly adapting the target domains by adaptively adjusting the parameters’ weights and position, respectively. For multifunctional learning, we proposed inter-function discriminator (IFD) that discriminates the classes by extracting inter-class common features and then subtracts them from both classes to avoid false prediction of the proposed model due to overfitting on the common features. Furthermore, we proposed a holistic-local fusion (HLF) module that exploits contextual-detailed features to adapt the scale-varying features across multiple functions. In addition, fractal dimension estimation (FDE) was employed for the classification of left-hand motor imagery (LMI) and right-hand motor imagery (RMI), confirming that proposed method can effectively extract the discriminative features for this task. The effectiveness of our proposed algorithm was assessed quantitatively and statistically against competent state-of-the-art (SOTA) algorithms utilizing three public datasets, demonstrating that our proposed algorithm outperformed SOTA algorithms.