A Small Object Detection Research Based on Dynamic Convolution Neural Network

In view of the fact that the detection effect of EfficientNet-YOLOv3 object detection algorithm is not very good, this paper proposes a small object detection research based on dynamic convolution neural network. Firstly, the dynamic convolutional neural network is introduced to replace the traditional, which makes the algorithm model more robust; secondly, the optimization parameters are continuously adjusted in the training process to further strengthen the model structure; finally, the Learning Rate and Batch Size parameters are modified during the training process in order to prevent overfitting. In order to verify the effectiveness of the proposed algorithm, RSOD and TGRS-HRRSD remote sensing image data sets are used to test the effect. The results of the proposed algorithm on RSOD remote sensing image data sets show that compared with the original EfficientNet-YOLOv3 algorithm, the mean Average Precision (mAP) value is increased by 1.93% and the mean Log Average Miss Rate (mLAMR) value is reduced by 0.0500; The results of the proposed algorithm on TGRS-HRRSD remote sensing image data set show that compared with the original EfficientNet-YOLOv3 algorithm, the mAP value is increased by 0.07% and the mLAMR value is reduced by 0.0007.

A robust approach for industrial small-object detection using an improved faster regional convolutional neural network

With the increasing pace in the industrial sector, the need for a smart environment is also increasing and the production of industrial products in terms of quality always matters. There is a strong burden on the industrial environment to continue to reduce impulsive downtime, concert deprivation, and safety risks, which needs an efficient solution to detect and improve potential obligations as soon as possible. The systems working in industrial environments for generating industrial products are very fast and generate products rapidly, sometimes leading to faulty products. Therefore, this problem needs to be solved efficiently. Considering this problem in terms of faulty small-object detection, this study proposed an improved faster regional convolutional neural network-based model to detect the faults in the product images. We introduced a novel data-augmentation method along with a bi-cubic interpolation-based feature amplification method. A center loss is also introduced in the loss function to decrease the inter-class similarity issue. The experimental results show that the proposed improved model achieved better classification accuracy for detecting our small faulty objects. The proposed model performs better than the state-of-the-art methods.

ECAP-YOLO: Efficient Channel Attention Pyramid YOLO for Small Object Detection in Aerial Image

Detection of small targets in aerial images is still a difficult problem due to the low resolution and background-like targets. With the recent development of object detection technology, efficient and high-performance detector techniques have been developed. Among them, the YOLO series is a representative method of object detection that is light and has good performance. In this paper, we propose a method to improve the performance of small target detection in aerial images by modifying YOLOv5. The backbone is was modified by applying the first efficient channel attention module, and the channel attention pyramid method was proposed. We propose an efficient channel attention pyramid YOLO (ECAP-YOLO). Second, in order to optimize the detection of small objects, we eliminated the module for detecting large objects and added a detect layer to find smaller objects, reducing the computing power used for detecting small targets and improving the detection rate. Finally, we use transposed convolution instead of upsampling. Comparing the method proposed in this paper to the original YOLOv5, the performance improvement for the mAP was 6.9% when using the VEDAI dataset, 5.4% when detecting small cars in the xView dataset, 2.7% when detecting small vehicle and small ship classes from the DOTA dataset, and approximately 2.4% when finding small cars in the Arirang dataset.

An Improved Swin Transformer-Based Model for Remote Sensing Object Detection and Instance Segmentation

Remote sensing image object detection and instance segmentation are widely valued research fields. A convolutional neural network (CNN) has shown defects in the object detection of remote sensing images. In recent years, the number of studies on transformer-based models increased, and these studies achieved good results. However, transformers still suffer from poor small object detection and unsatisfactory edge detail segmentation. In order to solve these problems, we improved the Swin transformer based on the advantages of transformers and CNNs, and designed a local perception Swin transformer (LPSW) backbone to enhance the local perception of the network and to improve the detection accuracy of small-scale objects. We also designed a spatial attention interleaved execution cascade (SAIEC) network framework, which helped to strengthen the segmentation accuracy of the network. Due to the lack of remote sensing mask datasets, the MRS-1800 remote sensing mask dataset was created. Finally, we combined the proposed backbone with the new network framework and conducted experiments on this MRS-1800 dataset. Compared with the Swin transformer, the proposed model improved the mask AP by 1.7%, mask APS by 3.6%, AP by 1.1% and APS by 4.6%, demonstrating its effectiveness and feasibility.

DeepSpot: a deep neural network for RNA spot enhancement in smFISH microscopy images

Detection of RNA spots in single molecule FISH microscopy images remains a difficult task especially when applied to large volumes of data. The small size of RNA spots combined with high noise level of images often requires a manual adaptation of the spot detection thresholds for each image. In this work we introduce DeepSpot, a Deep Learning based tool specifically designed to enhance RNA spots which enables spot detection without need to resort to image per image parameter tuning. We show how our method can enable the downstream accurate detection of spots. The architecture of DeepSpot is inspired by small object detection approaches. It incorporates dilated convolutions into a module specifically designed for the Context Aggregation for Small Object (CASO) and uses Residual Convolutions to propagate this information along the network. This enables DeepSpot to enhance all RNA spots to the same intensity and thus circumvents the need for parameter tuning. We evaluated how easily spots can be detected in images enhanced by our method, by training DeepSpot on 20 simulated and 1 experimental datasets, and have shown that more than 97% accuracy is achieved. Moreover, comparison with alternative deep learning approaches for mRNA spot detection (deepBlink) indicated that DeepSpot allows more precise mRNA detection. In addition, we generated smFISH images from mouse fibroblasts in a wound healing assay to evaluate whether DeepSpot enhancement can enable seamless mRNA spot detection and thus streamline studies of localized mRNA expression in cells.

Small object detection combining attention mechanism and a novel FPN

Since small objects occupy less pixels in the image and are difficult to recognize. Small object detection has always been a research difficulty in the field of computer vision. Aiming at the problems of low sensitivity and poor detection performance of YOLOv3 for small objects. AFYOLO, which is more sensitive to small objects detection was proposed in this paper. Firstly, the DenseNet module is introduced into the low-level layers of backbone to enhance the transmission ability of objects information. At the same time, a new mechanism combining channel attention and spatial attention is introduced to improve the feature extraction ability of the backbone. Secondly, a new feature pyramid network (FPN) is proposed to better obtain the features of small objects. Finally, ablation studies on ImageNet classification task and MS-COCO object detection task verify the effectiveness of the proposed attention module and FPN. The results on Wider Face datasets show that the AP of the proposed method is 11.89%higher than that of YOLOv3 and 8.59%higher than that of YOLOv4. All of results show that AFYOLO has better ability for small object detection.