Background subtraction by probabilistic modeling of patch features learned by deep autoencoders

García‐González, Jorge; Ortiz-de-Lazcano-Lobato, Juan Miguel; Luque‐Baena, Rafael Marcos; López‐Rubio, Ezequiel

doi:10.3233/ica-200621

Cited by 14 publications

(7 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Autoencoders training: Our proposal can be adapted to the sequence mainly in two ways: through the probabilistic model and by means of the specialisation of the DA. Other proposals ( [11,12]) only use a generic DA trained with generic images to encode the images from all sequences. In this work, in addition to the strategy of using the generic DA, two more strategies are tested in which a specific DA is trained for each sequence:…”

Section: Methodsmentioning

confidence: 99%

Moving Object Detection in Noisy Video Sequences Using Deep Convolutional Disentangled Representations

García‐González

Luque‐Baena

Ortiz-de-Lazcano-Lobato

et al. 2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Noise robustness is crucial when approaching a moving detection problem since image noise is easily mistaken for movement. In order to deal with the noise, deep denoising autoencoders are commonly proposed to be applied on image patches with an inherent disadvantage with respect to the segmentation resolution. In this work, a fully convolutional autoencoder-based moving detection model is proposed in order to deal with noise with no patch extraction required. Different autoencoder structures and training strategies are also tested to get insights into the best network design approach.

show abstract

Section: Methodsmentioning

confidence: 99%

Moving Object Detection in Noisy Video Sequences Using Deep Convolutional Disentangled Representations

García‐González

Luque‐Baena

Ortiz-de-Lazcano-Lobato

et al. 2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…Model-free frameworks are mainly based on deep learning approaches. They have achieved excellent applications in image object detection, image retrieval, video, and other fields with their strong learning ability (Benito-Picazo et al, 2020;García-González et al, 2020;Hamreras et al, 2020;Lara-Benítez et al, 2020;Simões et al, 2020;Sørensen et al, 2020;Thurnhofer-Hemsi et al, 2020;Vera-Olmos et al, 2019;Yang et al, 2019). In many fields of civil engineering, deep learning has achieved promising results, such as concrete compressive strength estimation (Rafiei et al, 2017), earthquake early warning (Rafiei & Adeli, 2017a), construction cost estimation (Rafiei & Adeli, 2018), sale prices estimation (Rafiei & Adeli, 2016), pavement roughness assessment (Jeong et al, 2020), and so on.…”

Section: F I G U R E 1 Different Image Sources For Pavement Distress Detectionmentioning

confidence: 99%

Cross‐scene pavement distress detection by a novel transfer learning framework

Che

Liu

et al. 2021

Computer aided Civil Eng

View full text Add to dashboard Cite

Deep learning has achieved promising results in pavement distress detection. However, the training model's effectiveness varies according to the data and scenarios acquired by different camera types and their installation positions. It is time consuming and labor intensive to recollect labeled data and retrain a new model every time the scene changes. In this paper, we propose a transfer learning pipeline to address this problem, which enables a distress detection model to be applied to other untrained scenarios. The framework consists of two main components: data transfer and model transfer. The former trains a generative adversarial network to transfer existing image data into a new scene style. Then, attentive CutMix and image melding are applied to insert distress annotations to synthesize the new scene's labeled data. After data expansion, the latter step transfers the feature extracted by the existing model to the detection application of the new scene through domain adaptation. The effects of varying degrees of knowledge transfer are also discussed. The proposed method is evaluated on two data sets from two different scenes with more than 40,000 images totally. This method can reduce the demand for training data by at least 25% when the model is applied in a new scene. With the same number of training images, the proposed method can improve the model accuracy by 26.55%.

show abstract

“…In the last few years, deep learning‐based methods, especially convolutional neural networks (CNNs), have emerged for object detection (Arabi et al, 2020; Reyes & Ventura, 2019; Vera‐Olmos et al, 2019) and other engineering fields (Benito‐Picazo et al, 2020; García‐González et al, 2020; Guo et al, 2021; Lara‐Benıtez et al, 2020; Mishra et al, 2020; Shen et al, 2019; T. Yang et al, 2019), so these methods have motivated object detection on construction sites. Currently, more pedestrian datasets such as the WIDER pedestrian challenge dataset (Loy et al, 2018) and better models for pedestrian detection (Bochkovskiy et al, 2020; Cai & Vasconcelos, 2019) are emerging.…”

Section: Literature Reviewmentioning

confidence: 99%

Deep learning‐based object identification with instance segmentation and pseudo‐LiDAR point cloud for work zone safety

Shen

Yan

Xiong

2021

Computer aided Civil Eng

View full text Add to dashboard Cite

Automated object identification in three‐dimensional (3D) space is crucial for work zone safety, such as compliance with construction rules and preventing workplace injuries and deaths. However, it is greatly challenged by some factors like high‐quality detection, high‐quality instance segmentation, few engineering object datasets with masks, and accurate 3D object understanding due to scale variations and limited cues in the 3D world. Traditional hand‐crafted methods suffer from these challenges. Our key insight is to use 2D object detection, instance segmentation and camera vision to compute pseudo‐light detection and ranging (LiDAR) point cloud for 3D object identification. On the one hand, an enhanced feature pyramid network is proposed to extract more fine‐grained object features, and an improved cascade mask R‐CNN is applied to detect bounding boxes and masks for all 2D objects efficiently. Moreover, the AIM dataset for heavy equipment detection is augmented, and a new object class with the bounding box and mask is added. On the other hand, pseudo‐LiDAR point clouds of objects based on bounding boxes and masks are recovered from a monocular image by deep learning, automatic camera parameter estimation, vision‐based method, and space filter. Extensive experiments and analyses show that the new methodology can identify 3D objects and automatically analyze work zone safety. The proposed object detection model has achieved state‐of‐the‐art results on the AIM dataset and 97.2% in mean average precision for the augmented dataset. The collision detection model using pseudo‐LiDAR point cloud has obtained 95.99% in accuracy. The new model will serve as a baseline to support 3D object identification research for other 3D tasks.

show abstract

Background subtraction by probabilistic modeling of patch features learned by deep autoencoders

Cited by 14 publications

References 38 publications

Moving Object Detection in Noisy Video Sequences Using Deep Convolutional Disentangled Representations

Moving Object Detection in Noisy Video Sequences Using Deep Convolutional Disentangled Representations

Cross‐scene pavement distress detection by a novel transfer learning framework

Deep learning‐based object identification with instance segmentation and pseudo‐LiDAR point cloud for work zone safety

Contact Info

Product

Resources

About