Detecting Small Signs from Large Images

Meng, Zibo; Fan, Xiaochuan; Chen, Xin; Chen, Min; Tong, Yan

doi:10.1109/iri.2017.57

Cited by 56 publications

(38 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We evaluate our proposed solutions described in Section III by performing experiments on the Bosch and Tsinghua-Tencent datasets. For training, we reduce the Tsinghua-Tencent dataset to 45 classes as done in [4], [12], [13]. We similarly limit the Bosch training dataset to 5 classes to avoid training on sparse classes.…”

Section: Methodsmentioning

confidence: 99%

A Hierarchical Deep Architecture and Mini-batch Selection Method for Joint Traffic Sign and Light Detection

Pon

Adrienko²,

Harakeh

et al. 2018

2018 15th Conference on Computer and Robot Vision (CRV)

View full text Add to dashboard Cite

Traffic light and sign detectors on autonomous cars are integral for road scene perception. The literature is abundant with deep learning networks that detect either lights or signs, not both, which makes them unsuitable for reallife deployment due to the limited graphics processing unit (GPU) memory and power available on embedded systems. The root cause of this issue is that no public dataset contains both traffic light and sign labels, which leads to difficulties in developing a joint detection framework. We present a deep hierarchical architecture in conjunction with a mini-batch proposal selection mechanism that allows a network to detect both traffic lights and signs from training on separate traffic light and sign datasets. Our method solves the overlapping issue where instances from one dataset are not labelled in the other dataset. We are the first to present a network that performs joint detection on traffic lights and signs. We measure our network on the Tsinghua-Tencent 100K benchmark for traffic sign detection and the Bosch Small Traffic Lights benchmark for traffic light detection and show it outperforms the existing Bosch Small Traffic light state-of-the-art method. We focus on autonomous car deployment and show our network is more suitable than others because of its low memory footprint and real-time image processing time. Qualitative results can be viewed at https://youtu.be/ YmogPzBXOw.

show abstract

Section: Methodsmentioning

confidence: 99%

A Hierarchical Deep Architecture and Mini-batch Selection Method for Joint Traffic Sign and Light Detection

Pon

Adrienko²,

Harakeh

et al. 2018

2018 15th Conference on Computer and Robot Vision (CRV)

View full text Add to dashboard Cite

show abstract

“…Li et al [29] proposed a Perceptual Generative Adversarial Network (Perceptual GAN) model that improves the detection accuracy of small traffic signs in the TT100K data set through narrowing the representation difference of small objects from large objects. Meng et al [30] used an expensive image pyramid and sliding window approach to achieve a recall of 0.93 and an accuracy of 0.90 on TT100K. Unfortunately, they did not provide the inference time.…”

Section: B Traffic Sign Detectionmentioning

confidence: 99%

Real-Time Detection Method for Small Traffic Signs Based on Yolov3

Zhang

Qin

et al. 2020

IEEE Access

View full text Add to dashboard Cite

It is very challenging to detect traffic signs using a high-precision real-time approach in realistic scenes with respect to driver-assistance systems for driving vehicles and autonomous driving. To address this challenge, in this paper, a new detection scheme (named MSA_YOLOv3) is proposed to accurately achieve real-time localization and classification of small traffic signs. First, data augmentation is achieved using image mixup technology. Second, a multi-scale spatial pyramid pooling block is introduced into the Darknet53 network to enable the network to learn object features more comprehensively. Finally, a bottomup augmented path is designed to enhance the feature pyramid in YOLOv3, and the result is to achieve accurate localization of objects by utilizing fine-grained features effectively in the lower layers. According to the tests on the TT100K dataset (which is a dataset for traffic sign detection), the performance of the proposed MSA_YOLOv3 is better than that of YOLOv3 in detecting small traffic signs. The detection speed of MSA_YOLOv3 is 23.81 FPS, and the mAP (mean Average Precision) reaches up to 86%.

show abstract

“…Generally, according to the literature [ 32 ], training examples were fewer compared to their dimensions, and the CNN training process led to an overfitted model. In addition, the recognition capabilities of such a model was degraded in cases when the subject of interest (defect) had an extremely small size compared to the entire input image [ 33 ]. Thus, the authors segmented each one of the CAD images into smaller ones to increase the number of data vectors, reduce their dimensions, and make the size of the defects comparable to image size.…”

Section: Approachmentioning

confidence: 99%

Deep Quality Assessment of a Solar Reflector Based on Synthetic Data: Detecting Surficial Defects from Manufacturing and Use Phase

Papacharalampopoulos

Tzimanis

Sabatakakis

et al. 2020

Sensors

View full text Add to dashboard Cite

Vision technologies are used in both industrial and smart city applications in order to provide advanced value products due to embedded self-monitoring and assessment services. In addition, for the full utilization of the obtained data, deep learning is now suggested for use. To this end, the current work presents the implementation of image recognition techniques alongside the original the quality assessment of a Parabolic Trough Collector (PTC) reflector surface to locate and identify surface irregularities by classifying images as either acceptable or non-acceptable. The method consists of a three-step solution that promotes an affordable implementation in a relatively small time period. More specifically, a 3D Computer Aided Design (CAD) of the PTC was used for the pre-training of neural networks, while an aluminum reflector surface was used to verify algorithm performance. The results are promising, as this method proved applicable in cases where the actual part was manufactured in small batches or under the concept of customized manufacturing. Consequently, the algorithm is capable of being trained with a limited number of data.

show abstract

Detecting Small Signs from Large Images

Cited by 56 publications

References 18 publications

A Hierarchical Deep Architecture and Mini-batch Selection Method for Joint Traffic Sign and Light Detection

A Hierarchical Deep Architecture and Mini-batch Selection Method for Joint Traffic Sign and Light Detection

Real-Time Detection Method for Small Traffic Signs Based on Yolov3

Deep Quality Assessment of a Solar Reflector Based on Synthetic Data: Detecting Surficial Defects from Manufacturing and Use Phase

Contact Info

Product

Resources

About