Attention-guided Image Captioning with Adaptive Global and Local Feature Fusion

AbstractVehicle re-identification (re-id) aims to solve the problems of matching and identifying the same vehicle under the scenes across multiple surveillance cameras. For public security and intelligent transportation system (ITS), it is extremely important to locate the target vehicle quickly and accurately in the massive vehicle database. However, re-id of the target vehicle is very challenging due to many factors, such as the orientation variations, illumination changes, occlusion, low resolution, rapid vehicle movement, and amounts of similar vehicle models. In order to resolve the difficulties and enhance the accuracy for vehicle re-id, in this work, we propose an improved multi-branch network in which global–local feature fusion, channel attention mechanism and weighted local feature are comprehensively combined. Firstly, the fusion of global and local features is adopted to obtain more information of the vehicle and enhance the learning ability of the model; Secondly, the channel attention module in the feature extraction branch is embedded to extract the personalized features of the targeting vehicle; Finally, the background and noise information on feature extraction is controlled by weighted local feature. The results of comprehensive experiments on the mainstream evaluation datasets including VeRi-776, VRIC, and VehicleID indicate that our method can effectively improve the accuracy of vehicle re-identification and is superior to the state-of-the-art methods.

Download Full-text

Vehicle Re-identification in Multi-branches Network

10.21203/rs.3.rs-598208/v1 ◽

2021 ◽

Author(s):

Leilei Rong ◽

Yan Xu ◽

Xiaolei Zhou ◽

Lisu Han ◽

Linghui Li ◽

...

Keyword(s):

Feature Extraction ◽

Feature Fusion ◽

State Of The Art ◽

Complete Information ◽

Local Feature ◽

Learning Ability ◽

Traffic Surveillance ◽

Illumination Changes ◽

Global And Local ◽

Vehicle Movement

Abstract Vehicle re-identification (Re-ID) aims to solve the problem of matching and identifying the same vehicles under the scene of cross multiple surveillance cameras. Finding the target vehicle quickly and accurately in the massive vehicle database is extremely important for public security, traffic surveillance and applications on smart city. However, it is very challenging due to the orientation variations, illumination changes, occlusion, low resolution, rapid vehicle movement, and amounts of similar vehicle models. In order to overcome these problems and improve the accuracy of vehicle re-identification, a multi-branches network is proposed, which is integrated by global-local feature fusion, channel attention mechanism, and weighted local feature. First, the fusion of global and local features is to obtain more complete information of the vehicle and enhance the learning ability of the model; second, the purpose of embedding the channel attention module in the feature extraction branch is to extract the personalized feature of the vehicle; finally, the influence of sky area and noise information on feature extraction is weakened by weighted local feature. The comprehensive experiments implemented on the mainstream evaluation datasets including VeRi-776, VRIC, and VehicleID indicate that our method can effectively improve the accuracy of vehicle re-identification and is superior to the state-of-the-art methods.

Download Full-text

AFGL-Net: Attentive Fusion of Global and Local Deep Features for Building Façades Parsing

Remote Sensing ◽

10.3390/rs13245039 ◽

2021 ◽

Vol 13 (24) ◽

pp. 5039

Author(s):

Dong Chen ◽

Guiqiu Xiang ◽

Jiju Peethambaran ◽

Liqiang Zhang ◽

Jing Li ◽

...

Keyword(s):

Feature Fusion ◽

State Of The Art ◽

Local Feature ◽

Global Features ◽

Learning Framework ◽

Building Facade ◽

Building Facades ◽

Feature Encoding ◽

Feature Aggregation ◽

Global And Local

In this paper, we propose a deep learning framework, namely AFGL-Net to achieve building façade parsing, i.e., obtaining the semantics of small components of building façade, such as windows and doors. To this end, we present an autoencoder embedding position and direction encoding for local feature encoding. The autoencoder enhances the local feature aggregation and augments the representation of skeleton features of windows and doors. We also integrate the Transformer into AFGL-Net to infer the geometric shapes and structural arrangements of façade components and capture the global contextual features. These global features can help recognize inapparent windows/doors from the façade points corrupted with noise, outliers, occlusions, and irregularities. The attention-based feature fusion mechanism is finally employed to obtain more informative features by simultaneously considering local geometric details and the global contexts. The proposed AFGL-Net is comprehensively evaluated on Dublin and RueMonge2014 benchmarks, achieving 67.02% and 59.80% mIoU, respectively. We also demonstrate the superiority of the proposed AFGL-Net by comparing with the state-of-the-art methods and various ablation studies.

Download Full-text