scholarly journals Improving Small Objects Detection using Transformer

2021 ◽  
Author(s):  
Shikha Dubey ◽  
Farrukh Olimov ◽  
Muhammad Aasim Rafique ◽  
Moongu Jeon
Keyword(s):  
Object Detection ◽  
Short Distance ◽  
Feature Fusion ◽  
Contextual Information ◽  
Spatial Association ◽  
Trade Off ◽  
Inductive Bias ◽  
Deep Layers ◽  
Bounding Boxes ◽  
Objects Detection

General artificial intelligence is a trade-off between the inductive bias of an algorithm and its out-of-distribution generalization performance. The conspicuous impact of inductive bias is an unceasing trend of improved predictions in various problems in computer vision like object detection. Although a recently introduced object detection technique, based on transformers (DETR), shows results competitive to the conventional and modern object detection models, its accuracy deteriorates for detecting small-sized objects (in perspective). This study examines the inductive bias of DETR and proposes a normalized inductive bias for object detection using a transformer (SOF-DETR). It uses a lazy-fusion of features to sustain deep contextual information of objects present in the image. The features from multiple subsequent deep layers are fused with element-wise-summation and input to a transformer network for object queries that learn the long and short-distance spatial association in the image by the attention mechanism.<br>SOF-DETR uses a global set-based prediction for object detection, which directly produces a set of bounding boxes. The experimental results on the MS COCO dataset show the effectiveness of the added normalized inductive bias and feature fusion techniques by detecting more small-sized objects than DETR. <br>

scholarly journals Improving Small Objects Detection using Transformer

2021 ◽  
Author(s):  
Shikha Dubey ◽  
Farrukh Olimov ◽  
Muhammad Aasim Rafique ◽  
Moongu Jeon
Keyword(s):  
Object Detection ◽  
Short Distance ◽  
Feature Fusion ◽  
Contextual Information ◽  
Spatial Association ◽  
Trade Off ◽  
Inductive Bias ◽  
Deep Layers ◽  
Bounding Boxes ◽  
Objects Detection

General artificial intelligence is a trade-off between the inductive bias of an algorithm and its out-of-distribution generalization performance. The conspicuous impact of inductive bias is an unceasing trend of improved predictions in various problems in computer vision like object detection. Although a recently introduced object detection technique, based on transformers (DETR), shows results competitive to the conventional and modern object detection models, its accuracy deteriorates for detecting small-sized objects (in perspective). This study examines the inductive bias of DETR and proposes a normalized inductive bias for object detection using a transformer (SOF-DETR). It uses a lazy-fusion of features to sustain deep contextual information of objects present in the image. The features from multiple subsequent deep layers are fused with element-wise-summation and input to a transformer network for object queries that learn the long and short-distance spatial association in the image by the attention mechanism.<br>SOF-DETR uses a global set-based prediction for object detection, which directly produces a set of bounding boxes. The experimental results on the MS COCO dataset show the effectiveness of the added normalized inductive bias and feature fusion techniques by detecting more small-sized objects than DETR. <br>

scholarly journals Improving Small Objects Detection using Transformer

2021 ◽  
Author(s):  
Shikha Dubey ◽  
Farrukh Olimov ◽  
Muhammad Aasim Rafique ◽  
Moongu Jeon
Keyword(s):  
Object Detection ◽  
Short Distance ◽  
Feature Fusion ◽  
Contextual Information ◽  
Spatial Association ◽  
Trade Off ◽  
Inductive Bias ◽  
Deep Layers ◽  
Bounding Boxes ◽  
Objects Detection

General artificial intelligence is a trade-off between the inductive bias of an algorithm and its out-of-distribution generalization performance. The conspicuous impact of inductive bias is an unceasing trend of improved predictions in various problems in computer vision like object detection. Although a recently introduced object detection technique, based on transformers (DETR), shows results competitive to the conventional and modern object detection models, its accuracy deteriorates for detecting small-sized objects (in perspective). This study examines the inductive bias of DETR and proposes a normalized inductive bias for object detection using a transformer (SOF-DETR). It uses a lazy-fusion of features to sustain deep contextual information of objects present in the image. The features from multiple subsequent deep layers are fused with element-wise-summation and input to a transformer network for object queries that learn the long and short-distance spatial association in the image by the attention mechanism.<br>SOF-DETR uses a global set-based prediction for object detection, which directly produces a set of bounding boxes. The experimental results on the MS COCO dataset show the effectiveness of the added normalized inductive bias and feature fusion techniques by detecting more small-sized objects than DETR. <br>

scholarly journals Object Detection Based on Global-Local Saliency Constraint in Aerial Images

2020 ◽  
Vol 12 (9) ◽  
pp. 1435 ◽  
Author(s):  
Chengyuan Li ◽  
Bin Luo ◽  
Hailong Hong ◽  
Xin Su ◽  
Yajun Wang ◽  
...  
Keyword(s):  
Object Detection ◽  
Semantic Information ◽  
Feature Fusion ◽  
Aerial Images ◽  
Natural Image ◽  
Optical Remote Sensing ◽  
Complex Background ◽  
Bounding Boxes ◽  
The Impact ◽  
Oriented Bounding Boxes

Different from object detection in natural image, optical remote sensing object detection is a challenging task, due to the diverse meteorological conditions, complex background, varied orientations, scale variations, etc. In this paper, to address this issue, we propose a novel object detection network (the global-local saliency constraint network, GLS-Net) that can make full use of the global semantic information and achieve more accurate oriented bounding boxes. More precisely, to improve the quality of the region proposals and bounding boxes, we first propose a saliency pyramid which combines a saliency algorithm with a feature pyramid network, to reduce the impact of complex background. Based on the saliency pyramid, we then propose a global attention module branch to enhance the semantic connection between the target and the global scenario. A fast feature fusion strategy is also used to combine the local object information based on the saliency pyramid with the global semantic information optimized by the attention mechanism. Finally, we use an angle-sensitive intersection over union (IoU) method to obtain a more accurate five-parameter representation of the oriented bounding boxes. Experiments with a publicly available object detection dataset for aerial images demonstrate that the proposed GLS-Net achieves a state-of-the-art detection performance.

scholarly journals Small Object Detection in Traffic Scenes Based on Attention Feature Fusion

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3031
Author(s):  
Jing Lian ◽  
Yuhang Yin ◽  
Linhui Li ◽  
Zhenghao Wang ◽  
Yafu Zhou
Keyword(s):  
Object Detection ◽  
Feature Fusion ◽  
Contextual Information ◽  
Detection Accuracy ◽  
Small Object ◽  
Limited Information ◽  
Feature Maps ◽  
Multi Scale ◽  
Validation Set ◽  
Small Object Detection

There are many small objects in traffic scenes, but due to their low resolution and limited information, their detection is still a challenge. Small object detection is very important for the understanding of traffic scene environments. To improve the detection accuracy of small objects in traffic scenes, we propose a small object detection method in traffic scenes based on attention feature fusion. First, a multi-scale channel attention block (MS-CAB) is designed, which uses local and global scales to aggregate the effective information of the feature maps. Based on this block, an attention feature fusion block (AFFB) is proposed, which can better integrate contextual information from different layers. Finally, the AFFB is used to replace the linear fusion module in the object detection network and obtain the final network structure. The experimental results show that, compared to the benchmark model YOLOv5s, this method has achieved a higher mean Average Precison (mAP) under the premise of ensuring real-time performance. It increases the mAP of all objects by 0.9 percentage points on the validation set of the traffic scene dataset BDD100K, and at the same time, increases the mAP of small objects by 3.5%.

scholarly journals SSD7-FFAM: A Real-Time Object Detection Network Friendly to Embedded Devices from Scratch

2021 ◽  
Vol 11 (3) ◽  
pp. 1096
Author(s):  
Qing Li ◽  
Yingcheng Lin ◽  
Wei He
Keyword(s):  
Object Detection ◽  
Real Time ◽  
Large Scale ◽  
Feature Fusion ◽  
Contextual Information ◽  
Attention Mechanism ◽  
Detection Accuracy ◽  
Single Shot ◽  
Feature Maps ◽  
Embedded Devices

The high requirements for computing and memory are the biggest challenges in deploying existing object detection networks to embedded devices. Living lightweight object detectors directly use lightweight neural network architectures such as MobileNet or ShuffleNet pre-trained on large-scale classification datasets, which results in poor network structure flexibility and is not suitable for some specific scenarios. In this paper, we propose a lightweight object detection network Single-Shot MultiBox Detector (SSD)7-Feature Fusion and Attention Mechanism (FFAM), which saves storage space and reduces the amount of calculation by reducing the number of convolutional layers. We offer a novel Feature Fusion and Attention Mechanism (FFAM) method to improve detection accuracy. Firstly, the FFAM method fuses high-level semantic information-rich feature maps with low-level feature maps to improve small objects’ detection accuracy. The lightweight attention mechanism cascaded by channels and spatial attention modules is employed to enhance the target’s contextual information and guide the network to focus on its easy-to-recognize features. The SSD7-FFAM achieves 83.7% mean Average Precision (mAP), 1.66 MB parameters, and 0.033 s average running time on the NWPU VHR-10 dataset. The results indicate that the proposed SSD7-FFAM is more suitable for deployment to embedded devices for real-time object detection.

scholarly journals SSD-TSEFFM: New SSD Using Trident Feature and Squeeze and Extraction Feature Fusion

Sensors ◽  
2020 ◽  
Vol 20 (13) ◽  
pp. 3630 ◽  
Author(s):  
Young-Joon Hwang ◽  
Jin-Gu Lee ◽  
Un-Chul Moon ◽  
Ho-Hyun Park
Keyword(s):  
Object Detection ◽  
Semantic Information ◽  
Feature Fusion ◽  
Contextual Information ◽  
Single Shot ◽  
Small Object ◽  
Dilated Convolution ◽  
Average Improvement ◽  
Proposed Model ◽  
Small Object Detection

The single shot multi-box detector (SSD) exhibits low accuracy in small-object detection; this is because it does not consider the scale contextual information between its layers, and the shallow layers lack adequate semantic information. To improve the accuracy of the original SSD, this paper proposes a new single shot multi-box detector using trident feature and squeeze and extraction feature fusion (SSD-TSEFFM); this detector employs the trident network and the squeeze and excitation feature fusion module. Furthermore, a trident feature module (TFM) is developed, inspired by the trident network, to consider the scale contextual information. The use of this module makes the proposed model robust to scale changes owing to the application of dilated convolution. Further, the squeeze and excitation block feature fusion module (SEFFM) is used to provide more semantic information to the model. The SSD-TSEFFM is compared with the faster regions with convolution neural network features (RCNN) (2015), SSD (2016), and DF-SSD (2020) on the PASCAL VOC 2007 and 2012 datasets. The experimental results demonstrate the high accuracy of the proposed model in small-object detection, in addition to a good overall accuracy. The SSD-TSEFFM achieved 80.4% mAP and 80.2% mAP on the 2007 and 2012 datasets, respectively. This indicates an average improvement of approximately 2% over other models.

scholarly journals Objects Detection Using Sensors Data Fusion in Autonomous Driving Scenarios

Electronics ◽  
2021 ◽  
Vol 10 (23) ◽  
pp. 2903
Author(s):  
Razvan Bocu ◽  
Dorin Bocu ◽  
Maksim Iavich
Keyword(s):  
Object Detection ◽  
Detection System ◽  
Autonomous Driving ◽  
3D Object ◽  
3D Objects ◽  
Autonomous Cars ◽  
Bounding Boxes ◽  
Objects Detection ◽  
3D Object Detection ◽  
Fine Tune

The relatively complex task of detecting 3D objects is essential in the realm of autonomous driving. The related algorithmic processes generally produce an output that consists of a series of 3D bounding boxes that are placed around specific objects of interest. The related scientific literature usually suggests that the data that are generated by different sensors or data acquisition devices are combined in order to work around inherent limitations that are determined by the consideration of singular devices. Nevertheless, there are practical issues that cannot be addressed reliably and efficiently through this strategy, such as the limited field-of-view, and the low-point density of acquired data. This paper reports a contribution that analyzes the possibility of efficiently and effectively using 3D object detection in a cooperative fashion. The evaluation of the described approach is performed through the consideration of driving data that is collected through a partnership with several car manufacturers. Considering their real-world relevance, two driving contexts are analyzed: a roundabout, and a T-junction. The evaluation shows that cooperative perception is able to isolate more than 90% of the 3D entities, as compared to approximately 25% in the case when singular sensing devices are used. The experimental setup that generated the data that this paper describes, and the related 3D object detection system, are currently actively used by the respective car manufacturers’ research groups in order to fine tune and improve their autonomous cars’ driving modules.

scholarly journals A Set of Single YOLO Modalities to Detect Occluded Entities via Viewpoint Conversion

2021 ◽  
Vol 11 (13) ◽  
pp. 6016
Author(s):  
Jinsoo Kim ◽  
Jeongho Cho
Keyword(s):  
Object Detection ◽  
Autonomous Vehicles ◽  
Autonomous Driving ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Cloud Data ◽  
Detection Techniques ◽  
Bounding Boxes ◽  
Partially Occluded ◽  
Rgb Image

For autonomous vehicles, it is critical to be aware of the driving environment to avoid collisions and drive safely. The recent evolution of convolutional neural networks has contributed significantly to accelerating the development of object detection techniques that enable autonomous vehicles to handle rapid changes in various driving environments. However, collisions in an autonomous driving environment can still occur due to undetected obstacles and various perception problems, particularly occlusion. Thus, we propose a robust object detection algorithm for environments in which objects are truncated or occluded by employing RGB image and light detection and ranging (LiDAR) bird’s eye view (BEV) representations. This structure combines independent detection results obtained in parallel through “you only look once” networks using an RGB image and a height map converted from the BEV representations of LiDAR’s point cloud data (PCD). The region proposal of an object is determined via non-maximum suppression, which suppresses the bounding boxes of adjacent regions. A performance evaluation of the proposed scheme was performed using the KITTI vision benchmark suite dataset. The results demonstrate the detection accuracy in the case of integration of PCD BEV representations is superior to when only an RGB camera is used. In addition, robustness is improved by significantly enhancing detection accuracy even when the target objects are partially occluded when viewed from the front, which demonstrates that the proposed algorithm outperforms the conventional RGB-based model.

Sign in / Sign up

Export Citation Format

Share Document