Search

Autonomous Fourier Ptychographic Microscopy (FPM) is a technology widely used in the field of pathology. It is compatible with high resolution and large field-of-view imaging and can observe more image details. Red blood cells play an indispensable role in assessing the oxygen-carrying capacity of the human body and in screening for clinical diagnosis and treatment needs. In this paper, the blood cell data set is constructed based on the FPM system experimental platform. Before training, four enhancement strategies are adopted for the blood cell image data to improve the generalization and robustness of the model. A blood cell detection algorithm based on SCD-YOLOv7 is proposed. Firstly, the C-MP (Convolutional Max Pooling) module and DELAN (Deep Efficient Learning Automotive Network) module are used in the feature extraction network to optimize the feature extraction process and improve the extraction ability of overlapping cell features by considering the characteristics of channels and spatial dimensions. Secondly, through the Sim-Head detection head, the global information of the deep feature map (mean average precision) and the local details of the shallow feature map are fully utilized to improve the performance of the algorithm for small target detection. MAP is a comprehensive indicator for evaluating the performance of object detection algorithms, which measures the accuracy and robustness of a model by calculating the average precision (AP) under different categories or thresholds. Finally, the Focal-EIoU (Focal Extended Intersection over Union) loss function is introduced, which not only improves the convergence speed of the model but also significantly improves the accuracy of blood cell detection. Through quantitative and qualitative analysis of ablation experiments and comparative experimental results, the detection accuracy of the SCD-YOLOv7 algorithm on the blood cell data set reached 92.4%, increased by 7.2%, and the calculation amount was reduced by 14.6 G.

Autonomous vehicles operating in public transportation spaces must rapidly and accurately detect all potential hazards in their surroundings to execute appropriate actions such as yielding, lane changing, and overtaking. This capability is a prerequisite for achieving advanced autonomous driving. In autonomous driving scenarios, distant objects are often small, which increases the risk of detection failures. To address this challenge, the MST-YOLOv8 model, which incorporates the C2f-MLCA structure and the ST-P2Neck structure to enhance the model’s ability to detect small objects, is proposed. This paper introduces mixed local channel attention (MLCA) into the C2f structure, enabling the model to pay more attention to the region of small objects. A P2 detection layer is added to the neck part of the YOLOv8 model, and scale sequence feature fusion (SSFF) and triple feature encoding (TFE) modules are introduced to assist the model in better localizing small objects. Compared with the original YOLOv8 model, MST-YOLOv8 demonstrates a 3.43% improvement in precision (P), an 8.15% improvement in recall (R), an 8.42% increase in mAP_0.5, a reduction in missed detection rate by 18.47%, a 70.97% improvement in small object detection AP, and a 68.92% improvement in AR.

Visual Place Recognition (VPR) aims to determine whether a robot or visual navigation system locates in a previously visited place using visual information. It is an essential technology and challenging problem in computer vision and robotic communities. Recently, numerous works have demonstrated that the performance of Convolutional Neural Network (CNN)-based VPR is superior to that of traditional methods. However, with a huge number of parameters, large memory storage is necessary for these CNN models. It is a great challenge for mobile robot platforms equipped with limited resources. Fortunately, Binary Neural Networks (BNNs) can reduce memory consumption by converting weights and activation values from 32-bit into 1-bit. But current BNNs always suffer from gradients vanishing and a marked drop in accuracy. Therefore, this work proposed a BinVPR model to handle this issue. The solution is twofold. Firstly, a feature restoration strategy was explored to add features into the latter convolutional layers to further solve the gradient-vanishing problem during the training process. Moreover, we identified two principles to address gradient vanishing: restoring basic features and restoring basic features from higher to lower layers. Secondly, considering the marked drop in accuracy results from gradient mismatch during backpropagation, this work optimized the combination of binarized activation and binarized weight functions in the Larq framework, and the best combination was obtained. The performance of BinVPR was validated on public datasets. The experimental results show that it outperforms state-of-the-art BNN-based approaches and full-precision networks of AlexNet and ResNet in terms of both recognition accuracy and model size. It is worth mentioning that BinVPR achieves the same accuracy with only 1% and 4.6% model sizes of AlexNet and ResNet.