Fast Simultaneous People Detection and Re-identification in a Single Shot Network

Ranst, Wiebe Van; Smedt, Floris De; Berte, Jonathan; Goedemé, Toon

doi:10.1109/avss.2018.8639489

Cited by 6 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the first, siamese or triplet networks are frequently suggested, as appearance cues are essential. The first approach introduced by [20] proposes a combination of the standard region loss with a triplet loss for maximising and minimising the distance between similar and dissimilar identities. In [21], authors propose deep collaborative reinforcement learning under a unified network.…”

Section: Trackingmentioning

confidence: 99%

Automatic Counting Passenger System Using Online Visual Appearance Multi-Object Tracking

Calle¹,

Sagastiberri²,

Aramburu³

et al. 2022

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

In recent years, people-counting problems have increased in popularity, especially in crowded indoor spaces, e.g., public transport. In peak hours, trains move significant numbers of passengers, producing delays and inconveniences for their users. Therefore, analysing how people use public transport is essential to solving this problem. The current analysis estimates how many people are inside a train station by using the number of people entering and leaving the ticket gates or estimating the train occupancy based on conventional CCTV cameras. However, this information is insufficient for knowing the train occupancy. The required data includes vehicle usage: how many people enter or leave a vehicle or which door is the most used. This paper presents a solution to the stated problem based on a multi-object tracker with a sequential visual appearance predictor and a line-based counting strategy to analyse each passenger's trajectory using an overhead fisheye camera. The camera selection inside the train was made after profoundly studying the railway environment. The method proposes a module to compute the total train occupancy. The solution is robust against occlusions thanks to the selected tracker and the fisheye camera field of view. This work shows a proof of concept dataset containing pseudo-real case scenarios of people's affluence in train doors recorded by fisheye cameras. Its purpose is to prove the system's functionality in these scenarios. The proposed approach achieved an overall accuracy of counting people getting on and off of 90.78% in the pseudo-real dataset, proving that this approach is valid.

show abstract

Section: Trackingmentioning

confidence: 99%

Automatic Counting Passenger System Using Online Visual Appearance Multi-Object Tracking

Calle¹,

Sagastiberri²,

Aramburu³

et al. 2022

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

show abstract

“…Several researchers have recently attempted this demanding challenge, i.e., building a model that can simultaneously learn multiple tasks with different outputs. Mousavian et al [310] undertook joint people detection in tandem with re-identification, while Van Ranst et al [311] tackled image segmentation with depth estimation. However, more exploration and investigation to overcome this challenge is needed.…”

Section: G Other Challengesmentioning

confidence: 99%

Survey on Multi-Output Learning

Shi

Tsang

et al. 2019

IEEE Trans. Neural Netw. Learning Syst.

162

View full text Add to dashboard Cite

The aim of multi-output learning is to simultaneously predict multiple outputs given an input. It is an important learning problem for decision-making, since making decisions in the real world often involves multiple complex factors and criteria. In recent times, an increasing number of research studies have focused on ways to predict multiple outputs at once. Such efforts have transpired in different forms according to the particular multi-output learning problem under study. Classic cases of multi-output learning include multi-label learning, multidimensional learning, multi-target regression and others. From our survey of the topic, we were struck by a lack in studies that generalize the different forms of multi-output learning into a common framework. This paper fills that gap with a comprehensive review and analysis of the multi-output learning paradigm. In particular, we characterize the 4 Vs of multi-output learning, i.e., volume, velocity, variety, and veracity, and the ways in which the 4 Vs both benefit and bring challenges to multioutput learning by taking inspiration from big data. We analyze the life cycle of output labeling, present the main mathematical definitions of multi-output learning, and examine the field's key challenges and corresponding solutions as found in the literature. Several model evaluation metrics and popular data repositories are also discussed. Last but not least, we highlight some emerging challenges with multi-output learning from the perspective of the 4 Vs as potential research directions worthy of further studies.

show abstract

“…It can improve the performance significantly when dataset of new tasks is limited. For example, adapting a network previously trained for image classification to facial expression recognition and person re-identification tasks [11]. Using this technique, knowledge of features that are discriminative for identities, attributes and semantic can transferred without any supervised learning for a new target domain [12].…”

Section: Related Workmentioning

confidence: 99%

Continuous Learning without Forgetting for Person Re-Identification

Sugianto

Tjondronegoro

Sorwar

et al. 2019

2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

View full text Add to dashboard Cite

Deep learning-based person re-identification faces a scalability challenge when the target domain requires continuous learning. Service environments, such as airports, need to recognize new visitors and add new cameras over time. Training-at-once is not enough to make the model robust to new tasks and domain variations. A well-known approach is fine-tuning, which suffers forgetting problem on old tasks when learning new tasks. Joint-training can alleviate the problem but requires old datasets, which is unobtainable in some cases. Recently, Learning without forgetting (LwF) shows its ability to mitigate the problem without old datasets. This paper extends the benefit of LwF from image classification to person re-identification with further challenges. Comprehensive experiments are based on Market1501 and DukeMTMC4ReID to evaluate and benchmark LwF to other approaches. The results confirm that LwF outperforms fine-tuning in preserving old knowledge and joint-training in faster training.

show abstract

Fast Simultaneous People Detection and Re-identification in a Single Shot Network

Cited by 6 publications

References 24 publications

Automatic Counting Passenger System Using Online Visual Appearance Multi-Object Tracking

Automatic Counting Passenger System Using Online Visual Appearance Multi-Object Tracking

Survey on Multi-Output Learning

Continuous Learning without Forgetting for Person Re-Identification

Contact Info

Product

Resources

About