Dans le mois de mai 2019 la Chaire présentera deux de ses travaux dans la conférence mondiale de transport organisée per Elsevier.

Les travaux présentés sont:

  • « Classifying logistic vehicles in cities using Deep learning » (S. Benslimane*, S. Tamayo, A. De La Fortelle)
  • « Food open-air markets in Paris: transportation environmental issues » (R. Benoit, C. Gunot, S. Tamayo*, A. Gaudron, F. Fontane)

Dans ce lien vous pouvez télécharger le programme de la conférence.

Ci après les résumés des travaux présentés  :

« Food open-air markets in Paris: transportation environmental issues »

Abstract— Food consumption habits have changed significantly in recent years due to the emergence of new distribution methods; such as shorter food supply chains. Today, consumers have access to a wide range of ways to do their groceries: online, through farm cooperatives and specialized stores. Historical vectors of food supply and representing a French-style “Art de Vivre”, local markets seem unshakeable and continue to play an important role in the lives of French citizens who seek to shop local. Faced with new consumer demands, local markets are looking to adapt to the changing habits of their customers, particularly in terms of environmental impacts. More specifically, Parisian markets are affected by the increasingly restrictive transportation environmental standards enforced by the city. Despite this, very few studies have been conducted on the real impact of the transport of food markets, which supply Parisians on a daily basis. They stand out from their regional counterparts, as the Ile-de- France region is not self-sufficient to feed all of its inhabitants, which results in only a small share of merchandise being sourced from local producers. Largely dependent on national agriculture and imports, the presence of the world’s largest fresh products market (Rungis International Market) reflects a steadily increasing need for one of the world’s most populous agglomerations. By means of a quantitative study, this article provides an initial assessment of the environmental impact of the regular maintenance of food markets and suggests potential development possibilities to maintain their activities while reducing their carbon footprint.

« Classifying logistic vehicles in cities using Deep learning »

Abstract— Rapid growth in delivery and freight transportation is increasing in urban areas; as a result the use of delivery trucks and light commercial vehicles is evolving. Major cities can use traffic counting as a tool to monitor the presence of delivery vehicles in order to implement intelligent city planning measures. Classical methods for counting vehicles use mechanical, electromagnetic or pneumatic sensors, but these devices are costly, difficult to implement and only detect the presence of vehicles without giving information about their category, model or trajectory. This paper proposes a Deep Learning tool for classifying vehicles in a given image while considering different categories of logistic vehicles, namely: light-duty, medium-duty and heavy-duty vehicles. The proposed approach yields two main contributions: first we developed an architecture to create an annotated and balanced database of logistic vehicles, reducing manual annotation efforts. Second, we built a classifier that accurately classifies the logistic vehicles passing through a given road. The results of this work are: first, a database of 72 000 images for 4 vehicles classes; and second two retrained convolutional neural networks (InceptionV3 and MobileNetV2) capable of classifying vehicles with accuracies over 90%.