Inception-SSD: An improved single shot detector for vehicle detection

Chen, Wanpei; Qiao, Yu; Li, Yujie

doi:10.1007/s12652-020-02085-w

Cited by 29 publications

(18 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Convolution Neural Networks (CNNs) have been proved to surpass humans on the ImageNet classification (He et al 2015a). According to our investigation, an increasing number of researchers have adopted CNNs to assist their research, such as morbidity identification (Kumar et al 2021), SAR image classification (Gao et al 2017a), vehicle detection (Chen et al 2020), wind turbine blade structural state evaluation (Sarkar and Gunturi 2020) and bridge crack detection (Xu et al 2019). These results suggest that CNNs could also be utilised to achieve high accuracy corrosion detection.…”

Section: Introductionmentioning

confidence: 92%

AMCD: an accurate deep learning-based metallic corrosion detector for MAV-based real-time visual inspection

Yang

Luo

et al. 2021

J Ambient Intell Human Comput

View full text Add to dashboard Cite

Corrosion has been concerned as a serious safety issue for metallic facilities. Visual inspection carried out by an engineer is expensive, subjective and time-consuming. Micro Aerial Vehicles (MAVs) equipped with detection algorithms have the potential to perform safer and much more efficient visual inspection tasks than engineers. Towards corrosion detection algorithms, convolution neural networks (CNNs) have enabled the power for high accuracy metallic corrosion detection. However, these detectors are restricted by MAVs on-board capabilities. In this study, based on You Only Look Once v3-tiny (Yolov3-tiny), an accurate deep learning-based metallic corrosion detector (AMCD) is proposed for MAVs on-board metallic corrosion detection. Specifically, a backbone with depthwise separable convolution (DSConv) layers is designed to realise efficient corrosion detection. The convolutional block attention module (CBAM), three-scale object detection and focal loss are incorporated to improve the detection accuracy. Moreover, the spatial pyramid pooling (SPP) module is improved to fuse local features for further improvement of detection accuracy. A field inspection image dataset labelled with four types of corrosions (the nubby corrosion, bar corrosion, exfoliation and fastener corrosion) is utilised for training and testing the AMCD. Test results show that the AMCD achieves 84.96% mean average precision (mAP), which outperforms other state-of-the-art detectors. Meanwhile, 20.18 frames per second (FPS) is achieved leveraging NVIDIA Jetson TX2, the most popular MAVs on-board computer, and the model size is only 6.1 MB.

show abstract

Section: Introductionmentioning

confidence: 92%

AMCD: an accurate deep learning-based metallic corrosion detector for MAV-based real-time visual inspection

Yang

Luo

et al. 2021

J Ambient Intell Human Comput

View full text Add to dashboard Cite

show abstract

“…Another primary requirement for transfer learning is the availability of pretrained models. Luckily, the deep learning community open-sourced many of the pretrained models such as VGG-16 [32], Inception [33], Deeplab [34], and MobileNet. The MobileNetv2 pretrained model has been adopted in the proposed method because of its significant fever parameters and minor computational complexity.…”

Section: Deep-learning Module (Dlm)mentioning

confidence: 99%

Transfer Learning Based Semantic Segmentation for 3D Object Detection from Point Cloud

Imad

Doukhi

Lee

2021

Sensors

View full text Add to dashboard Cite

Three-dimensional object detection utilizing LiDAR point cloud data is an indispensable part of autonomous driving perception systems. Point cloud-based 3D object detection has been a better replacement for higher accuracy than cameras during nighttime. However, most LiDAR-based 3D object methods work in a supervised manner, which means their state-of-the-art performance relies heavily on a large-scale and well-labeled dataset, while these annotated datasets could be expensive to obtain and only accessible in the limited scenario. Transfer learning is a promising approach to reduce the large-scale training datasets requirement, but existing transfer learning object detectors are primarily for 2D object detection rather than 3D. In this work, we utilize the 3D point cloud data more effectively by representing the birds-eye-view (BEV) scene and propose a transfer learning based point cloud semantic segmentation for 3D object detection. The proposed model minimizes the need for large-scale training datasets and consequently reduces the training time. First, a preprocessing stage filters the raw point cloud data to a BEV map within a specific field of view. Second, the transfer learning stage uses knowledge from the previously learned classification task (with more data for training) and generalizes the semantic segmentation-based 2D object detection task. Finally, 2D detection results from the BEV image have been back-projected into 3D in the postprocessing stage. We verify results on two datasets: the KITTI 3D object detection dataset and the Ouster LiDAR-64 dataset, thus demonstrating that the proposed method is highly competitive in terms of mean average precision (mAP up to 70%) while still running at more than 30 frames per second (FPS).

show abstract

“…Compared with conventional methods, CNN-based object detectors have gained significant improvements in vehicle detection. Deep learning-based vehicle detection approaches roughly fall into two main types of groups: one-stage detection approaches [26][27][28][29] and two-stage detection approaches [30][31][32][33]. The one-stage vehicle detection method does not need to choose candidate regions, but directly converts the classification and positions of the target into a regression problem.…”

Section: Related Workmentioning

confidence: 99%

A Nighttime Vehicle Detection Method with Attentive GAN for Accurate Classification and Regression

Liu

Qiu

Wang

et al. 2021

Entropy

View full text Add to dashboard Cite

Vehicle detection plays a vital role in the design of Automatic Driving System (ADS), which has achieved remarkable improvements in recent years. However, vehicle detection in night scenes still has considerable challenges for the reason that the vehicle features are not obvious and are easily affected by complex road lighting or lights from vehicles. In this paper, a high-accuracy vehicle detection algorithm is proposed to detect vehicles in night scenes. Firstly, an improved Generative Adversarial Network (GAN), named Attentive GAN, is used to enhance the vehicle features of nighttime images. Then, with the purpose of achieving a higher detection accuracy, a multiple local regression is employed in the regression branch, which predicts multiple bounding box offsets. An improved Region of Interest (RoI) pooling method is used to get distinguishing features in a classification branch based on Faster Region-based Convolutional Neural Network (R-CNN). Cross entropy loss is introduced to improve the accuracy of classification branch. The proposed method is examined with the proposed dataset, which is composed of the selected nighttime images from BDD-100k dataset (Berkeley Diverse Driving Database, including 100,000 images). Compared with a series of state-of-the-art detectors, the experiments demonstrate that the proposed algorithm can effectively contribute to vehicle detection accuracy in nighttime.

show abstract

Inception-SSD: An improved single shot detector for vehicle detection

Cited by 29 publications

References 22 publications

AMCD: an accurate deep learning-based metallic corrosion detector for MAV-based real-time visual inspection

AMCD: an accurate deep learning-based metallic corrosion detector for MAV-based real-time visual inspection

Transfer Learning Based Semantic Segmentation for 3D Object Detection from Point Cloud

A Nighttime Vehicle Detection Method with Attentive GAN for Accurate Classification and Regression

Contact Info

Product

Resources

About