Who is who at different cameras: people re-identification using depth cameras

Albiol, Antonio; Oliver, Javier; Mossi, José M.

doi:10.1049/iet-cvi.2011.0140

Cited by 38 publications

(46 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Table 2, we compare the re-identification rates achieved using the latent features with our previous work using explicit features or bodyprints [3]. It can be observed that the use of latent features has significantly improved the performance, which is mainly due to the fact that the latent features have naturally chosen the discriminative features that contain the relevant information.…”

Section: Resultsmentioning

confidence: 99%

“…The use of RGB-depth cameras has recently been proposed for person re-identification [3]. The use of these sensors eases the tasks of person segmentation and tracking and allows calibrated virtual views of the person to be created.…”

Section: Techniques For Person Re-identificationmentioning

confidence: 99%

“…Figure 1 shows the block diagram of the system for one camera node. After scene calibration [3], given the depth of a pixel (provided by the sensor), it is possible to obtain its height with respect to the ground. Knowing the height of every pixel allows a Height Map to be built [47].…”

Section: System Overviewmentioning

confidence: 99%

“…The bodyprint extraction also entails basic color normalization to deal with changes in illumination and cameras. For a more detailed explanation of this step, we encourage the reader to consult our previous work [3].…”

Section: System Overviewmentioning

confidence: 99%

“…Bodyprints were introduced in our previous work [3]. Although this descriptor achieves remarkable re-identification rates compared to other state-of-the-art methods, its performance may be degraded in complex scenarios by some environmental variables, such as non-uniformly distributed changes in illumination, the presence of carried objects, occlusions, etc.…”

Section: Motivationmentioning

confidence: 99%

See 4 more Smart Citations

Using latent features for short-term person re-identification with RGB-D cameras

Oliver

Albiol

et al. 2015

Pattern Anal Applic

View full text Add to dashboard Cite

This paper presents a system for people re-identification in uncontrolled scenarios using RGB-depth cameras. Compared to conventional RGB cameras, the use of depth information greatly simplifies the tasks of segmentation and tracking. In a previous work, we proposed a similar architecture where people were characterized using colorbased descriptors that we named bodyprints. In this work, we propose the use of latent feature models to extract more relevant information from the bodyprint descriptors by reducing their dimensionality. Latent features can also cope with missing data in case of occlusions. Different probabilistic latent feature models, such as Probabilistic Principal Component Analysis and Factor Analysis, are compared in the paper. The main difference between the models is how the observation noise is handled in each case. Re-identification experiments have been conducted in a real store where people behaved naturally. The results show that the use of the latent features significantly improves the re-identification rates compared to state-of-the-art works.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Techniques For Person Re-identificationmentioning

confidence: 99%

Section: System Overviewmentioning

confidence: 99%

Section: System Overviewmentioning

confidence: 99%

Section: Motivationmentioning

confidence: 99%

See 3 more Smart Citations

Using latent features for short-term person re-identification with RGB-D cameras

Oliver

Albiol

et al. 2015

Pattern Anal Applic

View full text Add to dashboard Cite

show abstract

Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-identification

Karianakis

Liu

Chen

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We address the problem of person re-identification from commodity depth sensors. One challenge for depth-based recognition is data scarcity. Our first contribution addresses this problem by introducing split-rate RGB-to-Depth transfer, which leverages large RGB datasets more effectively than popular fine-tuning approaches. Our transfer scheme is based on the observation that the model parameters at the bottom layers of a deep convolutional neural network can be directly shared between RGB and depth data while the remaining layers need to be fine-tuned rapidly. Our second contribution enhances re-identification for video by implementing temporal attention as a Bernoulli-Sigmoid unit acting upon frame-level features. Since this unit is stochastic, the temporal attention parameters are trained using reinforcement learning. Extensive experiments validate the accuracy of our method in person re-identification from depth sequences. Finally, in a scenario where subjects wear unseen clothes, we show large performance gains compared to a state-of-the-art model which relies on RGB data.

show abstract