CAD-to-real: enabling deep neural networks for 3D pose estimation of electronic control units

Image processing techniques are widely used within automotive series production, including production of electronic control units (ECUs). Deep learning approaches have made rapid advances during the last years, but are not prominent in those industrial settings yet. One major obstacle is the lack of suitable training data. We adapt the recently developed method of domain randomization to our use case of 3D pose estimation of ECU housings. We create purely synthetic data with high visual diversity to train artificial neural networks (ANNs). This enables ANNs to estimate the 3D pose of a real sample part with high accuracy from a single low-resolution RGB image in a production-like setting. Requirements regarding measurement hardware are very low. Our entire setup is fully automated and can be transferred to related industrial use cases.

Can Visual Aesthetic Components and Acceptance Be Traced Back to Forest Structure?

The importance of local forests as places of recreation and human well-being depends very much on their visual impact on human perception. Forest managers, therefore, seek to achieve structural elements or attributes that can be used to enhance the visual aesthetics of managed forest ecosystems. The following survey was undertaken in the Tharandter Forest in Saxony (Germany). The field interviews were focussed on visual aesthetics and acceptance. The statements of the 53 participants in the survey were used to analyse views concerning typical Norway spruce forest types: with the regeneration of deciduous tree species in the background, without regeneration, and with European beech as a second layer in the foreground. The evaluation of the questionnaires confirmed a clear ranking. The forest view with the regeneration of deciduous tree species received the highest number of positive scores, followed by the forest view with beech as a second layer. The forest view characterised by pure and dense Norway spruce trees received the worst rating, differing significantly from the other two, on the basis of the spatial arrangement, visual diversity and acceptance. Linear mixed models demonstrated that visual aesthetics was mostly explained by visual diversity as a result of tree species diversity or mixtures and age structures, the diversity of surrounding structures and colours, ground vegetation or visibility.

Action detection using a neural network elucidates the genetics of mouse grooming behavior

Automated detection of complex animal behaviors remains a challenging problem in neuroscience, particularly for behaviors that consist of disparate sequential motions. Grooming is a prototypical stereotyped behavior that is often used as an endophenotype in psychiatric genetics. Here, we used mouse grooming behavior as an example and developed a general purpose neural network architecture capable of dynamic action detection at human observer-level performance and operating across dozens of mouse strains with high visual diversity. We provide insights into the amount of human annotated training data that are needed to achieve such performance. We surveyed grooming behavior in the open field in 2457 mice across 62 strains, determined its heritable components, conducted GWAS to outline its genetic architecture, and performed PheWAS to link human psychiatric traits through shared underlying genetics. Our general machine learning solution that automatically classifies complex behaviors in large datasets will facilitate systematic studies of behavioral mechanisms.

The regulatory network for petal anthocyanin pigmentation is shaped by the MYB5a/NEGAN transcription factor in Mimulus

Much of the visual diversity of angiosperms is due to the frequent evolution of novel pigmentation patterns in flowers. The gene network responsible for anthocyanin pigmentation, in particular, has become a model for investigating how genetic changes give rise to phenotypic innovation. In the monkeyflower genus Mimulus, an evolutionarily recent gain of petal lobe anthocyanin pigmentation in M. luteus var. variegatus was previously mapped to genomic region pla2. Here, we use sequence and expression analysis, followed by transgenic manipulation of gene expression, to identify MYB5a—orthologous to the NEGAN transcriptional activator from M. lewisii—as the gene responsible for the transition to anthocyanin-pigmented petals in M. l. variegatus. In other monkeyflower taxa, MYB5a/NEGAN is part of a reaction-diffusion network that produces semi-repeating spotting patterns, such as the array of spots in the nectar guides of both M. lewisii and M. guttatus. Its co-option for the evolution of an apparently non-patterned trait—the solid petal lobe pigmentation of M. l. variegatus—illustrates how reaction-diffusion can contribute to evolutionary novelty in non-obvious ways. Transcriptome sequencing of a MYB5a RNAi line of M. l. variegatus reveals that this genetically simple change, which we hypothesize to be a regulatory mutation in cis to MYB5a, has cascading effects on gene expression, not only on the enzyme-encoding genes traditionally thought of as the targets of MYB5a but also on all of its known partners in the anthocyanin regulatory network.

SEMIOTICS IN THE WRAPPERS (CHADORSAHB) OF “TONEKABON” REGION UP TO “RUDSAR”

Wrapper weaving is an ancient art in the regions of East Guilan and West Mazandaran, in which the motifs used in it are woven according to the culture and customs of the people of these regions, which has made this feature unique in the wrapper. In this article, in addition to expressing the cultural aspects of the themes, an attempt has been made to study the visual diversity of the drawings along with its special feature in the wrapper.The hypothesis that is proven here is that the patterns characterize the simple way of thinking that is derived from nature and the environment around them.The research method is descriptive-analytical with field and library studies and is indepth.In general, the results indicate that the drawings used in the wrapper are inspired by the environment of the weavers and by the tools of the wrapper art itself.Also, the culture of symbols and signs in the art of wrapper weaving can be matched with the culture and traditions of other regions;This means that symbols and signs have a function beyond the clime of any region and can cover a large part of a land.Wrapper motifs in all weaves of the study, show the following of specific patterns along with symmetry, order and rhythm. Research method in the present study was done using the library and field methods.

A Statistical Growth Property of Plant Root Architectures

Numerous types of biological branching networks, with varying shapes and sizes, are used to acquire and distribute resources. Here, we show that plant root and shoot architectures share a fundamental design property. We studied the spatial density function of plant architectures, which specifies the probability of finding a branch at each location in the 3-dimensional volume occupied by the plant. We analyzed 1645 root architectures from four species and discovered that the spatial density functions of all architectures are population-similar. This means that despite their apparent visual diversity, all of the roots studied share the same basic shape, aside from stretching and compression along orthogonal directions. Moreover, the spatial density of all architectures can be described as variations on a single underlying function: a Gaussian density truncated at a boundary of roughly three standard deviations. Thus, the root density of any architecture requires only four parameters to specify: the total mass of the architecture and the standard deviations of the Gaussian in the three x,y,z growth directions. Plant shoot architectures also follow this design form, suggesting that two basic plant transport systems may use similar growth strategies.

Action detection using a neural network elucidates the genetics of mouse grooming behavior

Automated detection of complex animal behaviors remains a challenging problem in neuroscience, particularly for behaviors that consist of disparate sequential motions. Grooming, a prototypical stereotyped behavior, is often used as an endophenotype in psychiatric genetics. Using mouse grooming behavior as an example, we develop a general purpose neural network architecture capable of dynamic action detection at human observer-level performance and operate across dozens of mouse strains with high visual diversity. We provide insights into the amount of human annotated training data that are needed to achieve such performance. We survey grooming behavior in the open field in 2500 mice across 62 strains, determine its heritable components, conduct GWAS to outline its genetic architecture, and perform PheWAS to link human psychiatric traits through shared underlying genetics. Our general machine learning solution that automatically classifies complex behaviors in large datasets will facilitate systematic studies of mechanisms underlying these behaviors.

Jurnalisme investigasi televisi di Kompas TV Jakarta (Studi analisis isi kuantitatif pada naskah berita “Berkas Kompas”)

Lembaga penyiaran Televisi berupaya menyiarkan program yang diminati penonton. Program berita televisi disajikan dengan menyelidiki fakta dari sumber informasi yang kompeten. Agar dapat dipertanggungjawabkan, wartawan melakukan investigasi untuk mengetahui kebenaran informasi sebelum disiarkan. Program Berkas Kompas telah memperoleh penghargaan Piala Adinegoro pada tahun 2011 dan 2014., Winner Agrarian Reform Media Award 2018 dan Winner Anugerah Jurnalistik Polri 2018. Penelitian ini menggunakan metode Analisis Isi Kuantitatif dengan syarat tertulis dan terdokumentasi, menggunakan rumus Slovin untuk menentukan sampel. Teknik analisa data Uji Reliabilitas dengan Rumus Holsti. Penyajian berita pada acara “Berkas Kompas” dilihat dari sumber berita investigasi beritanya mayoritas berita melihat langsung dari media online. Reporter Berkas Kompas sebelum memilih materi berita melakukan hunting ke lapangan dan mencari materi melalui media online. Penyajian berita “Berkas Kompas” di Kompas TV Jakarta dilihat dari penelusuran narasumber memiliki ciri khas harus seimbang atau cover both side. Penyajian berita “Berkas Kompas” dilihat dari kualifikasi program investigasi mayoritas berita dengan sinkronisasi audio video terjaga dengan baik, dilihat dari keragaman/variasi narasumber, berita cukup seimbang, dan dilihat dari keragaman visual dan ungkapan narasi, berita cukup netral. Penyajian berita “Berkas Kompas” dilihat dari jenis kasus investigasi mayoritas dari sosial. Pertimbangan kebijakan redaksi liputan yang dilakukan berdasarkan pada mayoritas isu apa yang sedang berkembang. Television Investigation Journalism (Quantitative Content Analysis Study on the News Script "Berkas Kompas" AbstractTelevision broadcasting institutions try to broadcast programs that are of interest to the audience. Television news programs are served by investigating facts from competent sources of information. In order to be accounted for, journalists conduct investigations to find out the truth of the information before it is broadcast. Berkas Kompas Program has been awarded the Adinegoro Cup in 2011 and 2014, Winner of the 2018 Agrarian Reform Media Award and Winner of the 2018 National Police Journalistic Award. This research is a Quantitative Content Analysis Method research with written and documented requirements, using the Slovin formula to determine the sample. Data analysis techniques of Reliability Test is calculated with the Holsti Formula. The news presented in "Berkas Kompas" program, seen from investigative news sources, the majority of the news refer to online media. Before selecting the news materials, Berkas Kompas reporter is to get right in the field and search the news material through online media. The presentation of the "Berkas Kompas" news at Kompas TV Jakarta seen from the sources searching has a characteristic that must be balanced or cover both sides. The presentation of the "Berkas Kompas" seen from investigation program qualification shows that the majority of the news has well-maintained audio-video synchronization, seen from the diversity/variation of the sources, the news is quite balanced and seen from the visual diversity and narrative expressions, the news is quite neutral. The presentation of "Berkas Kompas" news seen from investigation case type shows that the majority is related to social issues. The considerations of the coverage editorial policy are based on the majority of issues that are developing.